01Agents
Tools
Agents and dev tools worth using, the releases that change the work, and status-page incidents worth watching.
Other
Claude code recomp of New Vegas
Win98 SPOOKY support posts a Claude code recomp of New Vegas — 37♥ / 6🔁 on Bluesky.
Kiro IDE 1.3.0 — Local Command Sandbox, Start Saved Workflows from Chat, Live Tab Status
Lets you limit what agent-run shell commands can reach, start saved Workflows from chat, and see live session status on editor tabs.
Run fast, private agents on-device with LFM2.5-24B-A2B
LiquidAI's LFM2.5-24B-A2B targets running agents on-device for private, local inference.
Open SWE: An Open-Source Framework for Internal Coding Agents
LangChain open-sources Open SWE, a framework for building internal coding agents.
Redesigning source control at Anthropic
Anthropic's merges per day grew more than tenfold and source control became its biggest development bottleneck; the post covers migrating to an in-house version control system in five months.
Copilot enterprise managed settings: force-refresh on startup, minimum client version
Two enforcement updates for enterprise-managed Copilot settings: managed settings now force-refresh on client startup, and a minimum required client version is enforced.
How to engineer an AI harness for game development
Builder essay on engineering an AI harness for game development — 136 points and 61 comments on HN, with the thread working through why LLMs fall over on game-y tasks.
Anthropic research: Distillation defenses
Anthropic says new methods reduced the amount of data harvested by distillers by around 90%, per early evidence in the Oct 12, 2026 post.
Cursor: Origin App Marketplace
Origin now integrates with over 20 apps for deployments, CI, code review, security, and monitoring.
Copilot: Client telemetry user attribution and configurable capture
Enterprise administrators can now use telemetry in managed settings to attribute GitHub Copilot client telemetry to users, with configurable capture.
Codex CLI installs a persistent, self-updating background daemon by default
425 points / 222 comments on HN. From the thread: there aren't any documented settings to disable this, but there is a feature flag it currently sits behind.
Kiro — Claude Opus 5.5 now available in AWS GovCloud (US)
Claude Opus 5.5 is now available in the Kiro IDE and CLI across both AWS GovCloud (US) Regions.
SWE-Duel: Towards a Self-Scaling Arena for Coding Agents
arXiv paper (submitted 8 Oct 2026) proposing SWE-Duel, a self-scaling arena for evaluating coding agents; authors Wei Minn, Zhensu Sun, Lwin Khin Shar, David Lo.
Gemini 4 Argon spotted in A/B testing on Antigravity
Reportedly reaching some users through A/B tests on Antigravity; early outputs shared on X look like a clear step up from Gemini 3.8 Flash. Spotted in testing — not a confirmed launch.
The gap in shared understanding of LLM capability is widening
HN thread (186 points, 285 comments) on Karpathy's argument that the gap in shared understanding of LLM capability is widening.
500B Tokens Later: Letting AI Agents Decompile a First-Person Shooter
HN thread (140 points, 103 comments) on using AI agents to decompile a first-person shooter after 500B tokens.
New controls and chat improvements in Copilot for JetBrains
New controls and chat improvements in Copilot for JetBrains, with user experience enhancements, quality improvements, and a deprecation in the same changelog entry — check what's deprecated before updating.
Kiro — Workflow Feedback, Power Search, and Flexible Hook Matching
Kiro CLI 2.29.0 introduces Memory for local V3 sessions — Kiro learns useful context from your work and recalls it in later chat sessions, with controls for memory access and automatic updates.
Use Your Claude Plan in Amp
Claude Pro/Max subscriptions can now be used in Amp — free and available for everyone. Pick Mode > Claude Code in a new thread (it sits on the main dial, no trip into 'Other Agents') and link your Claude sub.
My personal AI agent posted my bank details on company Slack
Business Insider first-person account: the author gave Grok Bot their financial details and connected it to work Slack, and the agent posted bank details to company Slack; 62 points / 66 comments on HN.
Talorys – A self-hosted personal AI agent on Cloudflare's free tier
A self-hosted personal AI agent that runs on Cloudflare's free tier, code on `github.com/rociiu` — 161 points and 86 comments on HN, with commenters arguing over whether Cloudflare-hosted counts as self-hosted at all.
openclaw
OpenClaw 2026.10.3
• OpenClaw 2026.10.3 updates that were stuck behind lost leases, completed-but-unrecognized receipts, or legacy 2026.9.8 activation records now recover and finish instead of refusing every retry. • Windows, macOS, and pnpm updates no longer leave the Gateway stopped or roll back: machine-qualified task accounts, short-name install paths, Doctor ancestry re-checks, protected Bun service commands, and pnpm 12 launchers all keep working. • Doctor no longer destroys data during repair: unreadable legacy auth keeps OAuth profiles, malformed UTF-8 memory files stay byte-exact, and blocked plugins ke
OpenClaw 2026.10.5-beta.3
• Updates leave the Gateway running: pnpm 12 installs keep their Gateway service and openclaw launcher on the durable install path, Windows updates accept qualified Scheduled Task accounts and their own verified driver, macOS accepts protected Bun service commands, and clean service-install refusals no longer leave the Gateway stopped. • Stuck updates recover: updates settle package-activation journals after filesystem remounts or device-number drift, ride out a briefly locked state database, stop reporting false post-install failures after migration, and reclaim retained updater runtimes that
OpenClaw 2026.10.5-beta.2
• Updates finish and recover: openclaw update settles stale handoff leases, completed receipts, and legacy 2026.9.8 recovery records instead of stopping on update-recovery-pending, keeps the service heap limit and webhook listeners, handles Windows short-name paths, and no longer reports accepted handoffs or successful updates as failures. • Doctor keeps your plugins and data: Doctor preserves installed plugins' configuration when path safety checks block them, leaves malformed UTF-8 root memory files untouched, and recovery copies capture Canvas and Memory Core files before migrations move th
OpenClaw 2026.10.2
• OpenClaw 2026.10.2: the first upgrade from stable 2026.10.1 now completes cleanly, successful in-place updates no longer end in errors, and Windows, cloned-filesystem, and private-Node update paths finish instead of stalling or rolling back. • Doctor no longer stops on residual legacy imports, stale Gateway locks, slow state inspection, memory reindex locks, or allowlists for removed channel accounts, and stale-receipt sessions keep their current data. • OpenAI and Anthropic API-key routes now default to provider-native compaction, and compaction recovers when the primary auth profile is coo
OpenClaw 2026.10.5-beta.1
• Safer updates: updates finish across devices, filesystems, Windows elevation, and interrupted activations, and recover from stale leases or changed evidence instead of stranding the install or blocking future updates. • Restart-safe conversations: interrupted turns, first messages during worktree preparation, and deferred tasks resume after a Gateway restart, and user input and committed session data survive restarts, concurrent writes, and failed publications. • Faster, steadier Gateway: session, transcript, history, and metadata reads move onto worker threads with far less SQLite work per
OpenClaw plugin SDK moves SQLite runtime writes into workers
Plugin SDK refactor (#168857) moves SQLite runtime writes into workers — a change to where plugin runtime writes are executed; worth retesting any OpenClaw plugin setup that uses SQLite.
OpenClaw 2026.10.1
• 2026.10.1-beta.2 is a hotfix beta covering 40 intervening commits since 2026.10.1-beta.1. • Updates and Doctor: recover archive migrations and interrupted updates without leaving managed Gateways stopped, and restore Gateway lifecycle commands on macOS 12 and disabled Windows tasks. • Replies and messaging: preserve completed answers after silent follow-ups, let Discord corrections pass deferred messages, and restore Telegram sends and buttons after channel-routed handoffs.
anomalyco
OpenCode 1.0.0
OpenCode 1.0.0 — the release is tagged vscode-v1.0.0, the VS Code extension.
OpenCode 1.19.0
• Version 1.19.0 • Run opencode upgrade --major to upgrade to OpenCode 2. • Allow the OpenAI ultrafast service tier.
NousResearch
Hermes Agent 0.22.0
• Hermes Agent v0.22.0. Release Date: October 13, 2026. • Since v0.21.0: ~24,200 commits · ~6,080 merged PRs · ~15,600 files changed · ~2,045,000 insertions · ~1,140,000 deletions · ~7,180 issues closed · ~2,520 contributors. • A fresh desktop install now opens on a guided setup chat that runs on a free trial model (nous/welcome, once per OS user), so a newcomer is talking to Hermes before they own an API key. Skip setup ends it and Settings → Run onboarding again brings it back. The agent also gained set_theme.
Hermes Agent 0.21.7
• Hermes Agent v0.21.7 is a patch release dated October 11, 2026. • This tag rolls up the ~204 PRs merged since v0.21.6 into a stable release for the desktop app (macOS Apple silicon, Windows), the Microsoft Store and MSIX, the installer, Docker and Hermes Cloud. • Updates now follow tagged releases. A source install of the official repository updates to the latest published vX.Y.Z release instead of every commit on main. An install already newer than the latest release stays where it is and waits for the next one; nothing is moved back. To keep following every commit: hermes update --set-chan
agno-agi
AGNO 3.1.3
• Version: 3.1.3. • Durable External Agent Sessions: ClaudeAgent sessions now resume on any replica. The Claude SDK session id is stored on the Agno session (#10903), and with PostgresDb, AsyncPostgresDb, SqliteDb, AsyncSqliteDb every transcript line is mirrored into the new agno_transcripts table. A stored session that cannot be resumed falls back to a fresh SDK session seeded with the Agno history. Claude and Codex non-streaming runs now keep tool calls and results in run history.…
anthropics
Claude Code 2.1.299
• Added CLAUDE_CODE_DISABLE_FILE_MENTIONS environment variable: Claude gets the paths of @ file mentions to read with its file tools, not the files' contents • Added idle compaction in the terminal: a 200K+ token conversation left idle for about 54 minutes is compacted before its one-hour prompt cache expires, so your next message doesn't reprocess it…
can1357
OMP 18.10.0
Raises the default context window for `openai-codex/gpt-6.1-sol` and `gpt-6.1-sol-wm` from 272K to 500K, matching OpenAI's new Codex default; extended context still opens 922K. Also adds `omp session pack`/`unpack`/`moved` to move a session with its artifacts to another machine (resuming the copy left behind forks it), `omp auth export`/`import` to carry model sign-ins, and `/fork` to create a new Tern pane while a turn is streaming.
cline
Cline 4.1.24
• Version 4.1.24. • With no model chosen, the Cline and OpenRouter providers now use Claude Sonnet 5.5. For Cline, that's the first model in Cline's recommended list. • Selecting ai& shows its own API key and model picker, instead of the generic OpenAI-compatible form with base URL and custom headers.
Ducksss
codex-profiles 1.3.0
Adds a native profile and workspace menu with usage, a `usage` CLI command for remaining Codex quota, low-quota alerts, and a Raycast extension for profiles and workspaces. Maintainer waived Desktop smoke checks — real Desktop behavior is unverified.
google-gemini
Gemini CLI 0.64.0 — atomic file writes, state corruption recovery
File tool operations are serialized and writes are atomic; CLI state persists atomically and recovers from backup on corruption; the CPU hang on @ within code is fixed. Also: folder trust state propagates in headless mode, a2a-server gains V1 to V2 settings migration, and ACP bridges PromptResponse.usage into usage_update notifications.
modelcontextprotocol
MCP servers v1.0.0
server-everything, server-filesystem, server-memory, and server-sequential-thinking publish at 1.0.0 on npm; mcp-server-fetch, mcp-server-git, and mcp-server-time publish at 2026.10.10 on PyPI. The everything server also cleans up subscriptions on session disconnect.
QwenLM
Qwen Code 0.25.1
• Version 0.25.1. • replace selected remote Hosts without losing bindings. • wait 60s before the E2E build artifact download retry (#13284).