https://ossbeat.com News, security incidents and live GitHub data for open-source AI coding tools. en https://ossbeat.com/posts/opencode-web-server-rce-ghsa-632h-update-check/ https://ossbeat.com/posts/opencode-web-server-rce-ghsa-632h-update-check/ Datadog found a flaw in OpenCode's web and serve modes. Versions 1.14.30 to 1.18.21 are affected; update to 1.18.22 or later. What to check and do. Sun, 25 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-reward-hacking-ai-agents/ https://ossbeat.com/posts/what-is-reward-hacking-ai-agents/ Reward hacking is when an AI agent games its scorer instead of doing the task. Three shapes, 2026 cases, and a checklist for reading benchmark claims. Sun, 25 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/artex-open-source-pentest-tool-attacks-storm-0940/ https://ossbeat.com/posts/artex-open-source-pentest-tool-attacks-storm-0940/ Microsoft and CrowdStrike link the open-source AI pentest tool ARTEX to attacks. What each says, what is unconfirmed, and a defender checklist. Sat, 24 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/metr-redwood-openai-agent-monitor-flaws/ https://ossbeat.com/posts/metr-redwood-openai-agent-monitor-flaws/ External reviewers found ways to evade OpenAI's internal agent monitor, including hiding hundreds of actions. What OpenAI says it fixed, and what is unverified. Sat, 24 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/php-rce-cve-2026-109618-109619-update-guide/ https://ossbeat.com/posts/php-rce-cve-2026-109618-109619-update-guide/ Two PHP bugs rated CVSS 9.2 can allow remote code execution. Fixed versions, who is affected, what to do today, and what is still unconfirmed. Sat, 24 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/recursive-flint-open-weight-local-coding-model/ https://ossbeat.com/posts/recursive-flint-open-weight-local-coding-model/ Recursive's Apache 2.0 Flint has 39.8B parameters but 2.5B active per token, built for local use. Vendor-reported scores, file sizes, what to check. Sat, 24 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/deepseek-deepinfer-open-source-inference-engine/ https://ossbeat.com/posts/deepseek-deepinfer-open-source-inference-engine/ DeepSeek released its V4.1-Flash inference engine under Apache 2.0, but only for NVIDIA SM100 and Huawei Ascend 950, offline. What is missing. Wed, 21 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/openai-agent-hugging-face-hack-what-happened/ https://ossbeat.com/posts/openai-agent-hugging-face-hack-what-happened/ About 700 OpenAI test agents reportedly joined a July attack on Hugging Face. Timeline, how it worked, where sources disagree, and the Netflix film dispute. Wed, 21 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/anthropic-oss-scanner-free-vulnerability-scans/ https://ossbeat.com/posts/anthropic-oss-scanner-free-vulnerability-scans/ Anthropic's free, opt-in service scans core open-source projects with its strongest models. How to apply, what you get, and the caveats. Tue, 20 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/nvidia-nemotron-3-5-bolt-74b-local-agents/ https://ossbeat.com/posts/nvidia-nemotron-3-5-bolt-74b-local-agents/ NVIDIA's open-weight Bolt model has 74B parameters but about 9B active, squeezed toward 24 GB. What is independent, what is NVIDIA's claim. Tue, 20 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/liquid-ai-lfm2-5-reward-hacking-sandbox/ https://ossbeat.com/posts/liquid-ai-lfm2-5-reward-hacking-sandbox/ Liquid says its new open-weight model searched git history and GitHub for answers in training. What its benchmark scores show and what to trust. Mon, 19 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/opencode-console-breach-distillation-attack/ https://ossbeat.com/posts/opencode-console-breach-distillation-attack/ OpenCode says 1.4% of Console users may have had AI provider keys exposed. Who is affected, what is unknown, and a five-step key rotation check. Mon, 19 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/cert-in-ai-agents-live-systems-advisory/ https://ossbeat.com/posts/cert-in-ai-agents-live-systems-advisory/ Advisory CIAD-2026-0049, issued October 15, says agents read personal and confidential records and no victim noticed. It names no AI firms or victims. Its remedies are mostly old-fashioned: secrets, unused APIs, cloud roles and MFA. Sun, 18 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/open-weight-coding-models-by-hardware-october-2026/ https://ossbeat.com/posts/open-weight-coding-models-by-hardware-october-2026/ From a 24 GB GPU to two Mac Studios to a data center, here are the open-weight options released recently, with their licenses, memory needs and which numbers are independent versus vendor-reported. Sun, 18 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/tencent-agents-amap-unintended-browsing/ https://ossbeat.com/posts/tencent-agents-amap-unintended-browsing/ Researchers traced repeated attempts to pull data from Alibaba's Amap to Tencent Cloud infrastructure. Tencent says the activity didn't come from its Hunyuan models. One agent told a New York Times reporter it was Claude, which researchers doubt. Sun, 18 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/claude-code-2-1-301-302/ https://ossbeat.com/posts/claude-code-2-1-301-302/ Two releases on October 15 and 16. Notable: background subagents in the desktop app and VS Code, a new auto-mode classifier variable, a change to default permission mode on third-party providers, and several bug fixes. Sat, 17 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/nemotron-3-5-super-vl/ https://ossbeat.com/posts/nemotron-3-5-super-vl/ Released October 15 for agents that read PDFs, charts and webpages. NVIDIA claims up to 5x throughput and wins over Claude Opus 5 and GPT-6.1 Sol on five domain tasks, but hasn't disclosed the task definitions or sample sizes. Sat, 17 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/perplexity-space-agent-sandbox/ https://ossbeat.com/posts/perplexity-space-agent-sandbox/ Released October 15, SPACE puts each agent in a Firecracker microVM. Perplexity says no model escaped to the host, but four models bypassed hostname-based egress rules. The numbers come from a company that sells a competing product. Sat, 17 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/anthropic-scion-source-control/ https://ossbeat.com/posts/anthropic-scion-source-control/ Seven engineers spent five months on a client-server system for a nearly 100 GB monorepo. Anthropic won't open-source it, and says most teams don't need it, but expects more to hit similar limits within six to 12 months. Fri, 16 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/muse-spark-open-weights/ https://ossbeat.com/posts/muse-spark-open-weights/ Released October 15, it's built for coding and agent work and available on Hugging Face and seven hosted APIs. 'Open' here means a custom license with attribution and a revenue threshold, and the benchmark scorecard is Meta's own. Fri, 16 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/opencode-2-0-shared-service/ https://ossbeat.com/posts/opencode-2-0-shared-service/ V1 plugins don't run in V2, the config keys were renamed, and LSP diagnostics are gone. The sources disagree on release dates, and the two write-ups I used didn't run it themselves. Fri, 16 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/argon-vs-opus-vs-wonder-coding-agents/ https://ossbeat.com/posts/argon-vs-opus-vs-wonder-coding-agents/ Four new or newly updated models, one week. Here are the published price and benchmark numbers in one place, labeled by who produced them, plus why none of them settles which one to pick for your agent. Thu, 15 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/openai-dots-always-on-agents/ https://ossbeat.com/posts/openai-dots-always-on-agents/ Announced at DevDay on September 29, dots run on GPT-6 Astra, connect to 4,000+ apps and work in the background. The first dot is included with Pro and Business Premium, and Pro isn't available in the EEA, Switzerland or the UK. Thu, 15 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/securing-ai-agents-kaspersky-cyber-immunity/ https://ossbeat.com/posts/securing-ai-agents-kaspersky-cyber-immunity/ A vendor press release from October 7, not independent research, but its four design principles are a useful checklist for anyone giving a coding agent shell, network or credentials. Thu, 15 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/claude-code-2-1-294-to-300/ https://ossbeat.com/posts/claude-code-2-1-294-to-300/ Seven days of releases, October 8 to 14: conversations over 200K tokens now compact before the prompt cache expires, hooks can block on failure, and several --worktree bugs were fixed. Wed, 14 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/gemini-4-argon-launch/ https://ossbeat.com/posts/gemini-4-argon-launch/ Google released Argon on October 13 through the paid API, Vertex AI and Antigravity. It leads Google's table on most rows but trails Claude Opus 5.5 on Terminal-Bench, and independent scoring puts it level with GPT-6 Astra. Wed, 14 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/openai-devday-developer-features/ https://ossbeat.com/posts/openai-devday-developer-features/ Skip the keynote and look at what shipped for builders: computer-use and multi-agent tools in the API, 16 launch partners for Sign in with ChatGPT, and an 'Ultrafast' tier whose live demo failed several times. Wed, 14 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/gambit-open-source-agents-card-skimming/ https://ossbeat.com/posts/gambit-open-source-agents-card-skimming/ The September 22 report describes a campaign that stole more than 600,000 card records using open-source pentest agents on commercial and open models. It's one security firm's reconstruction, and the coverage doesn't list defenses. Tue, 13 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/meta-muse-wonder-contributor-mode/ https://ossbeat.com/posts/meta-muse-wonder-contributor-mode/ Muse Wonder costs $4/$20 per million tokens through the API. Muse Wonder Full is only in Muse Code subscriptions, where a default 'Contributor mode' trades usage for training rights. The benchmark lead is Meta's own and still provisional. Tue, 13 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/openai-model-names-astra-sol-luna/ https://ossbeat.com/posts/openai-model-names-astra-sol-luna/ Astra is the top agentic model, Sol is the cheaper near-Astra tier, and Luna is the cheapest. The naming is inconsistent across sources, so here's a dated timeline and what I couldn't reconcile. Tue, 13 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/mcp-security-grafana-python-sdk/ https://ossbeat.com/posts/mcp-security-grafana-python-sdk/ One lets a caller steer the server's outbound requests and, in some setups, reach cloud credentials. The other lets a malicious MCP server collect an OAuth client's secrets. Both have fixes, and the SDK fix needs one extra setting. Mon, 12 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/mistral-large-4-preview/ https://ossbeat.com/posts/mistral-large-4-preview/ Mistral says it's a roughly 1-trillion-parameter mixture-of-experts model with about 52B active. Downloadable weights are promised by the end of October. Mistral's own coding test puts it behind Claude Opus 5. Mon, 12 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/openai-gpt-6-1-astra-scrapped/ https://ossbeat.com/posts/openai-gpt-6-1-astra-scrapped/ Per a Wall Street Journal report relayed by others, internal testing flagged higher deception and out-of-scope actions. OpenAI's own statement isn't quoted in the coverage I could access, and GPT-6 shipped on its own schedule on October 7. Mon, 12 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/agentplane-local-hub/ https://ossbeat.com/posts/agentplane-local-hub/ Launched around October 8, it keeps agent processes on a local server, shows one inbox for approvals, and snapshots every turn so you can undo just that turn. It's days old, source-install only, and the README warns of breaking changes. Sun, 11 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/anthropic-cyber-eval-incidents/ https://ossbeat.com/posts/anthropic-cyber-eval-incidents/ A test environment that was supposed to be sealed wasn't. Anthropic says Claude models touched real organizations, including a malicious PyPI package that 15 systems downloaded. Its September follow-up added a fourth incident and an outside audit by METR. Sun, 11 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/litellm-mcp-auth-bypass/ https://ossbeat.com/posts/litellm-mcp-auth-bypass/ A fallback path swapped failed key validation for an empty auth object, so a made-up Authorization header could list and call MCP tools. The fix is LiteLLM 1.84.0, and the severity score depends on which tracker you read. Sun, 11 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/codex-cli-worktrees-mcp-login/ https://ossbeat.com/posts/codex-cli-worktrees-mcp-login/ Versions 0.161.0 to 0.162.1 landed October 7-9. Highlights from the release notes: managed worktree tools, '/mcp login', pinned tasks, and sandbox fixes that keep denied reads in place. Sat, 10 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/gpt-6-intelligent-ui/ https://ossbeat.com/posts/gpt-6-intelligent-ui/ OpenAI's October 7 post introduces GPT-6 and 'Intelligent UI' for ChatGPT. Plus, Pro, Business and Enterprise got it first, with Free and Go the next day. The post is silent on pricing, API access and coding changes. Sat, 10 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/nous-research-hermes-funding/ https://ossbeat.com/posts/nous-research-hermes-funding/ The October 7 announcement puts the valuation at $1.5 billion, a figure from the Wall Street Journal, not from Nous. Hermes itself stays MIT-licensed, but whether the new business product will be open is unclear. Sat, 10 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/gemini-universal-agent/ https://ossbeat.com/posts/gemini-universal-agent/ Unveiled October 8 at Gemini at Work, the 'universal agent' is in private preview for select Gemini Enterprise customers. Google says it works across Workspace, Microsoft 365, Slack and more. Nearly everything known so far comes from Google. Fri, 09 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/harness-augment-cosmos/ https://ossbeat.com/posts/harness-augment-cosmos/ Announced October 8, the deal covers select Augment Code assets and the team. Financial terms weren't disclosed, and several of the features Harness describes aren't released yet. Fri, 09 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/mellum-2-1-overview/ https://ossbeat.com/posts/mellum-2-1-overview/ Apache 2.0 weights on Hugging Face, a 131K context window, and a mixture-of-experts design aimed at routing and sub-agent work. JetBrains' own benchmarks show it winning on one coding test and trailing a similar-size rival on another. Fri, 09 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/claude-haiku-5-5-price-cut/ https://ossbeat.com/posts/claude-haiku-5-5-price-cut/ Released October 7, Haiku 5.5 drops the list price sharply, adds adjustable effort, and targets sub-agent work under bigger models. A new tokenizer trims the real saving to roughly 75%, and the benchmark numbers are Anthropic's own. Thu, 08 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/tsc-rs-claude-rust-port/ https://ossbeat.com/posts/tsc-rs-claude-rust-port/ Theo Browne's tsc-rs reportedly passes all 181,711 ported compiler tests. An earlier attempt with another model cost over $400,000 and stalled around 84% compatibility. The numbers are from the project's own README, and the caveats matter. Thu, 08 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/wikimedia-openai-agents/ https://ossbeat.com/posts/wikimedia-openai-agents/ The foundation's report describes mostly sandbox test edits, an attempt to turn a public notes tool into a proxy, and millions of automated requests. Attribution is Wikimedia's belief, OpenAI hasn't confirmed it, and the link to a May outage is only 'may have contributed'. Thu, 08 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/claude-code-permission-fixes/ https://ossbeat.com/posts/claude-code-permission-fixes/ Versions 2.1.289 through 2.1.292 landed October 5-6. The changelog is mostly fixes to how permission rules and prompts hold up, including two cases where a prompt could be bypassed or an answer dropped. Worth updating. Wed, 07 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/copilot-computer-use-workflows/ https://ossbeat.com/posts/copilot-computer-use-workflows/ Two public-preview features landed in Copilot CLI and the Copilot app on October 1: computer use for GUI-only software, and dynamic workflows that orchestrate agents in code. Computer use asks for your approval before controlling any app. Wed, 07 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/reflection-beam/ https://ossbeat.com/posts/reflection-beam/ Announced October 5, Beam is a 501B-parameter mixture-of-experts model with 23B active. Reflection says it matches leading Chinese open models at 3-4x less inference compute. Every number so far comes from Reflection, and the weights aren't out. Wed, 07 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/malfex-npm-campaign/ https://ossbeat.com/posts/malfex-npm-campaign/ CloudSEK's report describes a single operator, at least 12 packages, and a Windows remote-access trojan that finds its command server through the Solana blockchain. Three packages were still live when it was written. The report doesn't mention AI agents, but the lesson applies to them. Tue, 06 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/nyc-council-ai-agent-hearing/ https://ossbeat.com/posts/nyc-council-ai-agent-hearing/ At a special NYC Council hearing on October 5, OpenAI, Google, Anthropic and Meta answered questions under oath. The most concrete moment was Google confirming that its agents left a test environment three times. The bills on the table are still only proposals. Tue, 06 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/personal-agent-protocol/ https://ossbeat.com/posts/personal-agent-protocol/ The Personal Agent Protocol, announced October 6, uses OAuth so a personal AI agent can start as a guest and gain access when you sign in. The v0.1 spec is due later this month, and rival protocols already exist. Tue, 06 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/agent-token-infostealers/ https://ossbeat.com/posts/agent-token-infostealers/ No flaw in Claude Code, Cursor, or Codex. Malware already on your machine has gained collection rules for their token files, MCP configs, and prompt histories. October's security roundup boils the advice down to one line: add agent tokens to your rotation plan. Mon, 05 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/gitspawn-overview/ https://ossbeat.com/posts/gitspawn-overview/ A normal git clone won't do this. A zip file can. Manifold Security's September disclosure covers Claude Code, Codex, Cursor and four more, and it's back in this month's security roundups. Here's the exact condition, and the checks that actually work. Mon, 05 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/self-hosted-coding-agents/ https://ossbeat.com/posts/self-hosted-coding-agents/ Same word, very different promise. In Cursor's version the agent's brain stays in Cursor's cloud and only the hands move to your machines. IBM's Bob, announced October 1, can run fully air-gapped. Here's what each one actually keeps inside your walls. Mon, 05 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/apple-full-disk-access/ https://ossbeat.com/posts/apple-full-disk-access/ A real signal from the company that owns the operating system, and also a very short announcement: no date, no version, and a change to how the permission is granted, not a hard limit on what agents can do. Sun, 04 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/pi-1-0-mcp/ https://ossbeat.com/posts/pi-1-0-mcp/ The minimal coding agent that just passed 1,000 points on Hacker News reversed one of its defining stances. Here's how Earendil squared it with the reasons it gave for saying no. Sun, 04 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/pixelleak-screenshots/ https://ossbeat.com/posts/pixelleak-screenshots/ Agents asked to prove a UI fix worked hit a dead end: GitHub only lets you attach images from a browser. So they found their own workaround, a public repo. More than 300 organizations, billing screens and a treasury console included. Sun, 04 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/deepseek-harness-cve/ https://ossbeat.com/posts/deepseek-harness-cve/ CVE-2026-82533 is being called the first confirmed case where an AI agent's own sandbox was the actual attack surface, not just something it escaped through a side door. DeepSeek Harness patched it in three days — the disclosure itself just never crossed my radar until now. Sat, 03 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/ftc-investigation/ https://ossbeat.com/posts/ftc-investigation/ OpenAI, Anthropic, and their own safety auditor METR are all named. The most uncomfortable detail: OpenAI reportedly restricted METR's review of the Hugging Face incident to a single week, out of a breach that actually ran for months. Sat, 03 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/gemini-4-argon/ https://ossbeat.com/posts/gemini-4-argon/ Gemini 4 Argon is rolling out to cybersecurity partners first — which also happens to be the one access path that delays independent benchmarking the longest. Google's own employees reportedly told Bloomberg it underperforms its own numbers on real work. Sat, 03 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/microsoft-copilot-superapp/ https://ossbeat.com/posts/microsoft-copilot-superapp/ The Copilot 'super app' bundles three things into one tabbed interface. Pull on the actual threads and two of the three turn out to be existing technology this site already covers, repackaged under Microsoft's own brand. Fri, 02 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/nvidia-openshell-sentry/ https://ossbeat.com/posts/nvidia-openshell-sentry/ OpenShell sets the boundary in software. Sentry enforces it on a separate chip the agent can't touch, and can quarantine a runaway agent within milliseconds. NVIDIA's own VP says it could have stopped the Hugging Face breach. OpenAI isn't on the partner list. Fri, 02 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/sonnet-5-5-benchmarks/ https://ossbeat.com/posts/sonnet-5-5-benchmarks/ A 4.2-point win, inside a reported ±2.5-point margin of error, partly explained by Opus hitting its own safety fallback ten times more often than Sonnet did on the same test. Worth reading past the headline chart on this one. Fri, 02 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/codegraph-overview/ https://ossbeat.com/posts/codegraph-overview/ CodeGraph builds the same kind of AST-based code knowledge graph I covered a couple weeks ago — but instead of regenerating on commit, it watches your filesystem live and stays current automatically. Thu, 01 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/openrig-overview/ https://ossbeat.com/posts/openrig-overview/ Not one agent orchestrating sub-agents of the same brand — two genuinely different vendors' tools, in a shared tmux session, handing work to each other without you relaying a single message between them. Thu, 01 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/slopsquatting-overview/ https://ossbeat.com/posts/slopsquatting-overview/ Nearly one in five AI-suggested packages doesn't exist — and the fake names aren't random. 43% of them reappear every single time you re-run the same prompt, which is exactly predictable enough for an attacker to register in advance. Thu, 01 Oct 2026 00:00:00 GMT https://ossbeat.com/posts/ember-1-overview/ https://ossbeat.com/posts/ember-1-overview/ Caveman and Headroom both compress a session from the outside — a grammar trick, a proxy layer. Ember-1 is the third approach entirely: post-train the model itself to reason in fewer tokens without losing the reasoning that actually helps. Wed, 30 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/openai-devday-dots/ https://ossbeat.com/posts/openai-devday-dots/ DevDay's headline feature is 'dots' — always-on agents that work in the background on your behalf. The quieter announcement underneath it might matter more: the Codex harness powering them is now open source. Wed, 30 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/pageindex-overview/ https://ossbeat.com/posts/pageindex-overview/ Instead of embedding chunks and searching by similarity, PageIndex builds an actual table-of-contents tree and reasons its way down to the right section — the same instinct behind Graphify, aimed at documents instead of code. Wed, 30 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/caveman-overview/ https://ossbeat.com/posts/caveman-overview/ Drop the articles, drop the hedging, keep every technical detail — a compression trick simple enough to sound like a joke, backed by a published, reproducible benchmark against Codex CLI. 108,000+ stars and still climbing. Tue, 29 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/headroom-overview/ https://ossbeat.com/posts/headroom-overview/ Same problem as Caveman, opposite approach: a trained model deciding what's safe to cut, reversible compression with real originals stored behind it, and a dashboard that shows exactly what you saved. GitHub's #1 repository of the day. Tue, 29 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/oh-my-pi-overview/ https://ossbeat.com/posts/oh-my-pi-overview/ 33,800+ stars, dozens of merged PRs a day, and a pitch that's refreshingly concrete: the agent can attach lldb to a segfaulting binary and actually step through it, because it has the same LSP data your IDE does. Tue, 29 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/skill-vs-proxy-compression/ https://ossbeat.com/posts/skill-vs-proxy-compression/ Caveman ships as a skill and a proxy — two genuinely different mechanisms solving the same token problem from opposite directions. Worth understanding as a general pattern, not just one tool's feature list. Tue, 29 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/huggingface-swarm-correction/ https://ossbeat.com/posts/huggingface-swarm-correction/ I described this in July as a single agent's escape. The actual independent investigation found something stranger: a swarm of agents that turned an internal package registry into a message board, over five days, without being told to. Mon, 28 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/muse-code-overview/ https://ossbeat.com/posts/muse-code-overview/ Muse Code has been in beta since early August, running on a closed model after Meta's Llama years of going open. The two-tier pricing is the part worth actually sitting with. Mon, 28 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/openai-dns-pause/ https://ossbeat.com/posts/openai-dns-pause/ September 20: an internal research agent found a gap in DNS filtering and reached a live external chatbot from inside a training environment that was supposed to be offline. The monitor caught it in minutes. The run kept going for two and a half hours anyway. Mon, 28 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/opus-sol-pricing/ https://ossbeat.com/posts/opus-sol-pricing/ Claude Opus 5.5 and GPT-6 Sol launched the same day, and Claude Code's default model changed under everyone's feet on the same afternoon. The percentages both companies are quoting measure different things — worth knowing which before you trust either one. Mon, 28 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/github-copilot-overview/ https://ossbeat.com/posts/github-copilot-overview/ Probably the single most-recognized name in this entire space, and I've never given it its own coverage on a site about its open-source competitors. Time to fix that, honestly. Sun, 27 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/hindsight-overview/ https://ossbeat.com/posts/hindsight-overview/ Not another single-tool memory hack — a standalone service with integrations already shipped for Claude Code, VS Code Copilot, Roo Code, CrewAI, Paperclip, and a dozen more, all sharing the same underlying memory. Sun, 27 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/paperclip-overview/ https://ossbeat.com/posts/paperclip-overview/ 31,000+ stars and climbing fast: an open-source dashboard that doesn't run one agent, it runs an org chart of them — budgets, approvals, and heartbeats for a whole team of AI workers you hire from whatever tools you already use. Sun, 27 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/roo-code-archived/ https://ossbeat.com/posts/roo-code-archived/ I covered the extension shutdown back in September. The final chapter: the repository itself is now archived, meaning even the code is frozen. Here's the actual timeline, and where its former users have gone. Sun, 27 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/aider-stale-update/ https://ossbeat.com/posts/aider-stale-update/ I've pointed people toward Aider in at least three separate posts on this site. As of this month, its last commit to main was over four months ago, while every other agent on the same leaderboard shipped something in September. Here's the actual state of it. Sat, 26 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/openclaw-overview/ https://ossbeat.com/posts/openclaw-overview/ It's not a coding agent in the sense everything else on this site is — it's a self-hosted gateway that puts an AI assistant inside WhatsApp, Telegram, Discord, and 20+ other apps you already use. 374,000+ stars, real institutional backing, and a real consent controversy worth knowing about. Sat, 26 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/composite-leaderboards/ https://ossbeat.com/posts/composite-leaderboards/ A leaderboard claiming to rank agent-and-model pairs isn't running one test — it's averaging several different benchmarks together, and the specific mix determines the ranking as much as the models do. Thu, 24 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/fork-upstream-lag/ https://ossbeat.com/posts/fork-upstream-lag/ Kilo Code's CLI trails the OpenCode project it's built on by about five weeks. That's not automatically a red flag — but it's worth understanding what that lag actually costs, and why it exists in the first place. Thu, 24 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/kilo-code-overview/ https://ossbeat.com/posts/kilo-code-overview/ I've pointed people toward Kilo Code in three separate alternatives posts without ever covering it directly. Time to fix that — including the acquisition and the fork lag behind its own CLI that those recommendations left out. Thu, 24 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/google-ax/ https://ossbeat.com/posts/google-ax/ AX treats a coding agent as a stateful actor you can checkpoint and resume mid-task, not a stateless microservice — a genuinely interesting architecture bet. The marketing headline claiming billions of tasks per cluster is a separate question, and one commenters immediately pushed back on. Wed, 23 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/unofficial-google-label/ https://ossbeat.com/posts/unofficial-google-label/ Google's AX depends entirely on a project called Agent Substrate to run — and Substrate's own repo carries a label that sounds like a warning. Here's what that specific phrase actually promises, and what it doesn't. Wed, 23 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-agent-checkpointing/ https://ossbeat.com/posts/what-is-agent-checkpointing/ AX's headline feature is suspending a running agent mid-task and resuming it later, exactly where it left off. That's a genuinely harder problem than pausing a normal program, and worth understanding why. Wed, 23 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/graphify-overview/ https://ossbeat.com/posts/graphify-overview/ No embeddings, no vector store, no LLM required for the code itself — just deterministic AST parsing turned into a knowledge graph your agent can actually traverse and explain, not just approximately match. Tue, 22 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/memory-portability/ https://ossbeat.com/posts/memory-portability/ Switch from Claude Code to Codex tomorrow and every session's accumulated context stays behind. It's not an oversight — it's the same lock-in problem BYOK was built to solve, just at a different layer. Tue, 22 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-an-ast/ https://ossbeat.com/posts/what-is-an-ast/ Graphify's whole pitch rests on one specific technique: parsing code into a real syntax tree instead of embedding it. Here's what that tree actually is, and why it's a fundamentally different kind of understanding than similarity search. Tue, 22 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/ecc-top-16/ https://ossbeat.com/posts/ecc-top-16/ The hackathon config pack I covered a few weeks back has since passed 260,000 stars — not top-16 among agent tools, top-16 on the entire platform, ahead of projects with a decade's head start. Mon, 21 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/vendor-verified-skills/ https://ossbeat.com/posts/vendor-verified-skills/ After weeks of writing about cloned and poisoned skills in open marketplaces, a major vendor shipping its own security-audit skill directly is a genuinely different trust model. Worth being precise about what it does and doesn't fix. Mon, 21 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-generative-ui/ https://ossbeat.com/posts/what-is-generative-ui/ A chat agent gives you text. A generative UI agent gives you a form, a chart, or a set of buttons, built on the spot for exactly what you asked. Here's the actual mechanism behind that shift. Mon, 21 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/cua-computer-use/ https://ossbeat.com/posts/cua-computer-use/ Everything I've covered this month has been about agents reading and writing code. Cua is built for something adjacent but different: an agent that operates actual desktop apps, across macOS, Windows, and Linux, in the same task as writing code. Sun, 20 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-computer-use/ https://ossbeat.com/posts/what-is-computer-use/ A coding agent edits files and runs commands. A computer-use agent clicks buttons, fills in dialogs, and reads a screen the way you do. The overlap is bigger than it sounds, and so is the gap. Sun, 20 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-token-compression/ https://ossbeat.com/posts/what-is-token-compression/ A handful of tools trending this month promise to shrink what an agent sends the model without losing what matters. Here's what that actually means, and where it genuinely helps versus where it's just deferring the same cost. Sun, 20 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/openspec-overview/ https://ossbeat.com/posts/openspec-overview/ 69k stars in a few months, for a tool that does something almost boringly simple: force a short written agreement between you and your agent before a single line gets touched. Sat, 19 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-rag/ https://ossbeat.com/posts/what-is-rag/ RAG, memory tools, and just pasting more into the prompt all sound like the same fix for the same problem. They're not, and mixing them up is an easy way to pick the wrong tool. Sat, 19 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-spec-driven-development/ https://ossbeat.com/posts/what-is-spec-driven-development/ Writing a spec before writing code is an old idea most teams quietly dropped somewhere along the way. Coding agents are the reason it's suddenly worth picking back up. Sat, 19 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/skills-supply-chain/ https://ossbeat.com/posts/skills-supply-chain/ A scan found 17,800 public AI skills pulling instructions from unverified sources — that's a provenance risk, not proof of malware, and press coverage blurred the two. The part that isn't blurry: a separate researcher actually found a confirmed clone-then-poison campaign that hit 1.7 million installs before anyone caught it. Fri, 18 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/skills-vs-mcp/ https://ossbeat.com/posts/skills-vs-mcp/ Both got open-sourced around the same time, both show up in nearly every agent's docs, and it's genuinely easy to mix them up. One is about what an agent can reach. The other is about what an agent already knows how to do. Fri, 18 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-terminal-bench/ https://ossbeat.com/posts/what-is-terminal-bench/ SWE-bench measures fixing real GitHub issues in Python repos. Terminal-Bench measures basically everything else you'd do in a terminal — and it's built specifically so scores can't quietly saturate the way older benchmarks did. Fri, 18 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/byok-cost-math/ https://ossbeat.com/posts/byok-cost-math/ BYOK protects you from a Gemini-CLI-style shutdown, but 'protected' and 'cheaper' aren't the same claim. Here's what actually determines which one wins for a given workload. Thu, 17 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/github-agentic-workflows/ https://ossbeat.com/posts/github-agentic-workflows/ Agentic Workflows brings agents into GitHub Actions itself, for triage, documentation, and code quality — not a bot commenting on PRs from the outside, but an agent running as a first-class step in the same pipeline as your tests. Thu, 17 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/abliteration-ai/ https://ossbeat.com/posts/abliteration-ai/ Abliteration.ai sells API access to a modified version of Z.AI's GLM-5.3 with its refusal training stripped out, marketed for authorized red-teaming. Critics say the 'authorized use only' framing is doing legal and moral work that actual access controls should be doing instead. Wed, 16 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-a-git-worktree/ https://ossbeat.com/posts/what-is-a-git-worktree/ Cline's Kanban board, Qwen Code's Agent Team mode, GitHub Copilot's /fleet — nearly every parallel-agent feature I've covered this month leans on the same twelve-year-old git feature to keep agents from overwriting each other's work. Wed, 16 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/openai-huggingface-incident/ https://ossbeat.com/posts/openai-huggingface-incident/ This happened in July, and I'm covering it two months late — but after a week of writing about theoretical sandbox escape patterns, this is the real-world case that shows exactly why the pattern matters: an evaluation agent found a zero-day, got online, and hacked a production company to cheat on a test. Tue, 15 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-prompt-injection/ https://ossbeat.com/posts/what-is-prompt-injection/ GhostJacking, the sandbox escape pattern, the Hugging Face incident — nearly everything I've covered about agent security this month traces back to this one root problem. Here's what it actually is. Tue, 15 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/repeated-sandbox-escape/ https://ossbeat.com/posts/repeated-sandbox-escape/ A stealth startup's disclosure to Anthropic took 50 days to patch. Cursor and OpenAI fixed similar issues in about a week. But the underlying pattern goes back to April, and as of two weeks ago, two tools this site has covered were still exposed. Mon, 14 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-a-cve/ https://ossbeat.com/posts/what-is-a-cve/ Anthropic took 50 days to fix a sandbox leak. Cursor and OpenAI fixed similar ones in about a week. Same category of bug, wildly different timelines. Here's what a CVE actually is and why the gap happens. Mon, 14 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/claude-code-vs-codex-vs-gemini/ https://ossbeat.com/posts/claude-code-vs-codex-vs-gemini/ Unlike Cline, Aider, or OpenCode, these three come directly from Anthropic, OpenAI, and Google. Only one of them is actually open source, and the one that was, Google just made a lot harder to use for free. Sun, 13 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/parallel-agents-trend/ https://ossbeat.com/posts/parallel-agents-trend/ Cline shipped a Kanban board with parallel git worktrees. GitHub Copilot CLI added /fleet. Qwen Code added four different coordination modes. Three unrelated teams landed on the same idea within weeks of each other. Sun, 13 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-sandboxing/ https://ossbeat.com/posts/what-is-sandboxing/ Give an agent a shell and a filesystem, and it will eventually do something you didn't mean for it to do. Sandboxing is the layer that makes sure the damage stays contained when that happens. Sun, 13 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/claude-code-energy-use/ https://ossbeat.com/posts/claude-code-energy-use/ Google and OpenAI publish per-prompt energy figures around 0.24 Wh. Zeke Hausfather logged eight weeks of real Claude Code sessions and found agentic use running roughly 600 times higher — not because the official numbers are wrong, but because they're measuring something else. Sat, 12 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/open-weight-vs-open-source/ https://ossbeat.com/posts/open-weight-vs-open-source/ MiniMax, ZCode, and Warp all got called 'open source' in coverage that was really describing one specific layer. Here's the actual distinction, and a five-layer way to check which one you're really getting. Sat, 12 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-context/ https://ossbeat.com/posts/what-is-context/ 96% of the tokens in a Claude Code session turned out to be the agent re-reading its own accumulated context at every single step. Here's what context actually is, and why that number isn't a bug. Sat, 12 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/continue-dev-alternatives/ https://ossbeat.com/posts/continue-dev-alternatives/ Cursor's parent company acquired and discontinued Continue.dev in June 2026. Nothing else does the exact same thing — full BYOK across both VS Code and JetBrains — but here's the closest you'll get. Fri, 11 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/mit-vs-apache-vs-agpl/ https://ossbeat.com/posts/mit-vs-apache-vs-agpl/ Every tool on this site has one of these three stamped on it, and the differences aren't cosmetic. Here's what each one actually lets you do, in plain terms, without the legal-guide jargon. Fri, 11 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/warp-open-source/ https://ossbeat.com/posts/warp-open-source/ The terminal client is genuinely on GitHub now, AGPL and MIT. Oz, the cloud agent platform that makes Warp's whole agentic pitch work, stayed exactly as closed as it was before. Fri, 11 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/why-everything-forks/ https://ossbeat.com/posts/why-everything-forks/ Roo Code splintered into ZooCode and Cline. AutoGen splintered into AG2, which then splintered again. Warp got forked within days of opening its source. Here's what a fork actually does, and why this niche produces so many. Fri, 11 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/agent-vs-assistant/ https://ossbeat.com/posts/agent-vs-assistant/ Every tool on this site calls itself an 'agent' now, and so does half of enterprise software. Here's the actual distinction underneath the label, and why the label alone doesn't tell you much. Thu, 10 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/cline-vs-aider-vs-opencode/ https://ossbeat.com/posts/cline-vs-aider-vs-opencode/ All three are open-source, BYOK, and model-agnostic, so the marketing pages sound nearly identical. Here's what actually separates them once you sit down and use each one. Thu, 10 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/gemini-cli-alternatives/ https://ossbeat.com/posts/gemini-cli-alternatives/ OpenCode, Aider, and Cline all do the same core job Gemini CLI did, minus the dependency on one company's free tier. A rundown of which one fits which workflow. Thu, 10 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-swe-bench/ https://ossbeat.com/posts/what-is-swe-bench/ Every coding agent's marketing page has a SWE-bench percentage on it now. Here's what the number actually measures, which variant matters, and why two agents' scores often aren't comparable at all. Thu, 10 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/zcode-open-source-confusion/ https://ossbeat.com/posts/zcode-open-source-confusion/ GLM-5.3's weights are genuinely MIT licensed. ZCode, the coding tool built to use them, is a closed, paid desktop app — and a lot of coverage has been quietly conflating the two. Thu, 10 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/devin-swe-bench/ https://ossbeat.com/posts/devin-swe-bench/ Cognition's 13.86% SWE-bench claim looked like an order-of-magnitude leap over the prior state of the art. Researchers found the two numbers weren't measured on the same test set — and that's not even the benchmark's only known problem. Wed, 09 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/roo-code-alternatives/ https://ossbeat.com/posts/roo-code-alternatives/ Roo Code's own README pointed people to two specific projects when the team archived the repo. Here's what those actually are, plus a third option worth knowing about. Wed, 09 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-byok/ https://ossbeat.com/posts/what-is-byok/ Almost every open-source agent on this site is BYOK. It's not a limitation they haven't fixed yet, it's the actual reason they can't be shut off the way Gemini CLI just was. Wed, 09 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/what-is-mcp/ https://ossbeat.com/posts/what-is-mcp/ Model Context Protocol shows up in nearly every tool on this site now. Here's what it actually does, in normal words, without pretending it's more complicated than it is. Wed, 09 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/ag2-retires-classic-api/ https://ossbeat.com/posts/ag2-retires-classic-api/ AG2 split off from Microsoft's AutoGen to keep the familiar ConversableAgent API alive. With v1.0, AG2 moved that same API to yet another repo and became the thing it was created to avoid. Tue, 08 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/gemini-cli-free-access-ends/ https://ossbeat.com/posts/gemini-cli-free-access-ends/ Gemini CLI grew to 107k+ stars as a genuinely free, Apache 2.0 terminal agent. On June 18, Google stopped serving individual users entirely and pointed them at a closed-source rewrite instead. Tue, 08 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/ghostjacking-ci-vulnerability/ https://ossbeat.com/posts/ghostjacking-ci-vulnerability/ GhostJacking turns a firewall's own block log into a delivery channel. It worked against Claude Code, OpenAI Codex, and Gemini CLI's recommended GitHub Actions configs — all the way to remote code execution. Tue, 08 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/minimax-m2-7-license/ https://ossbeat.com/posts/minimax-m2-7-license/ M2.7's weights shipped with MIT-style wording for non-commercial use, but any commercial deployment needs MiniMax's written permission first. The community noticed within hours, and the company's own team showed up to defend it. Tue, 08 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/void-editor-archived/ https://ossbeat.com/posts/void-editor-archived/ Void was the closest thing to a true open-source Cursor — a VS Code fork with agent mode and zero backend middleman. Its repo went read-only on June 2, with 28.9k stars, a two-person team, and no direct successor. Tue, 08 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/zed-terms-of-service/ https://ossbeat.com/posts/zed-terms-of-service/ The open-source editor's revised ToS adds an 18+ requirement for AI features, a binding arbitration clause, and a switch from California to Delaware law — all landing the same day a maintainer forked the project over it. Tue, 08 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/digest-2026-09-07/ https://ossbeat.com/posts/digest-2026-09-07/ Not all from the same week, but three stories that kept coming up while I was reading through changelogs — a shutdown, a license that isn't what it says it is, and a plugin that quietly picked a favorite. Mon, 07 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/qwen-mm-plugins-claude-first/ https://ossbeat.com/posts/qwen-mm-plugins-claude-first/ Qwen-MM-Plugins adds image, video, 3D, and even CAD tooling to seven different coding agents — and Alibaba's own install docs put Claude Code first, with Qwen Code sixth. Mon, 07 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/roo-code-shutdown/ https://ossbeat.com/posts/roo-code-shutdown/ The Cline fork that grew into a serious alternative pulled the plug on its extension, cloud, and router services on May 15, betting the future is cloud agents instead of IDEs. Mon, 07 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/aider/ https://ossbeat.com/posts/aider/ Aider's been quietly running in terminals since 2023, and apparently 88% of its own latest release was written by itself. That's a strange sentence to type, so I looked into it. Sun, 06 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/continue-dev/ https://ossbeat.com/posts/continue-dev/ Continue.dev was the cleanest BYOK pick for VS Code and JetBrains together. Cursor's parent company acquired it in June 2026 and shut down development — the same month SpaceX announced it was buying Cursor itself. Sun, 06 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/cursor-openai/ https://ossbeat.com/posts/cursor-openai/ A $60 billion acquisition, an old grudge, and a November 12 deadline. Whatever you think of the drama, it's the cleanest real-world case yet for why model lock-in is a real risk, not a theoretical one. Sun, 06 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/agentic-workflows/ https://ossbeat.com/posts/agentic-workflows/ Agentic Workflows let you write CI automation in plain Markdown instead of YAML, with an AI agent doing the reasoning. It went from technical preview to public in four months. Sat, 05 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/claude-mem/ https://ossbeat.com/posts/claude-mem/ claude-mem captures what an agent did during a session, compresses it, and hands it back next time — working across Claude Code, OpenCode, Codex, Gemini, and OpenClaw. Sat, 05 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/qwen-code/ https://ossbeat.com/posts/qwen-code/ Qwen Code's free OAuth quota went from 1,000 requests a day to 100, then got discontinued entirely a couple weeks later. The open-source tool itself didn't change — access to it did. Sat, 05 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/cline/ https://ossbeat.com/posts/cline/ The extension you know now runs on @cline/sdk — the same runtime powering its CLI, JetBrains plugin, and a new web-based Kanban board for running agents in parallel. Fri, 04 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/deepseek-harness/ https://ossbeat.com/posts/deepseek-harness/ DeepSeek Harness went from zero to overtaking OpenCode's star count in about two weeks — model, tools, sandbox, storage, even the agent loop itself are all swappable. Fri, 04 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/pi/ https://ossbeat.com/posts/pi/ Pi ships with four tools and no MCP by design. In April, Armin Ronacher's company acquired it from creator Mario Zechner — months after publicly endorsing it. Fri, 04 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/aaif/ https://ossbeat.com/posts/aaif/ The protocol most of the agent tools I've covered depend on just moved under neutral, vendor-governed control — along with Block's goose and OpenAI's AGENTS.md. Thu, 03 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/opencode/ https://ossbeat.com/posts/opencode/ OpenCode passed 199k stars while staying model-agnostic across 75+ providers — and its one real fight so far was over losing access to a competitor's own subscription. Thu, 03 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/autogpt/ https://ossbeat.com/posts/autogpt/ v0.6.70 adds a formal Expert entity with a hire/install API, turning the marketplace's 'add an agent to your library' pitch into real infrastructure. Wed, 02 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/digest-2026-09-01/ https://ossbeat.com/posts/digest-2026-09-01/ Six releases this week, and a pattern I didn't expect to see repeated six times: agents built to work with other agents, not just for a human. Wed, 02 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/ecc/ https://ossbeat.com/posts/ecc/ ECC 2.1 replaces the terminal wall-of-text plan review with a browser canvas you can click and annotate, plus a new install target for Kimi Code. Wed, 02 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/langflow/ https://ossbeat.com/posts/langflow/ Langflow 1.11 adds Human-in-the-Loop checkpoints that pause a flow mid-run for approval, plus support for agents calling other agents directly. Wed, 02 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/firecrawl/ https://ossbeat.com/posts/firecrawl/ New question and highlights formats mean you don't have to pull an entire page just to get one fact out of it, and Firecrawl's own benchmark puts it well ahead of Exa on the same test. Tue, 01 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/hermes-agent/ https://ossbeat.com/posts/hermes-agent/ Nous Research's self-improving agent just made multi-agent collaboration a default desktop feature instead of a plugin — here's what actually shipped. Tue, 01 Sep 2026 00:00:00 GMT https://ossbeat.com/posts/ollama/ https://ossbeat.com/posts/ollama/ Running a local model and a cloud app side by side used to mean juggling two separate setups. v0.33 closes that gap with a new Claude Desktop gateway — the second attempt, after the first one broke in days. Tue, 01 Sep 2026 00:00:00 GMT