openclaw / ui
AGENTS.md394k starsChanged todayMITView on GitHub
The Control UI and its plugin views use Solid 2 and native primitives; never add Lit or Web Awesome. Solid route modules expose renderSolid(props) from the existing lazy page import. The outlet mounts that renderer once and supplies live data, loaderPending, and presented props; loader updates must preserve page-local state. Keep page imports inside their route's component loader.
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 5
Before writing, reviewing, or refactoring any Solid code here, read the Solid skill in full, the installed …
≈ “Common” is an estimate: at least 1 in 5 of the 36,368 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Control UI Guide
Solid
- Before writing, reviewing, or refactoring any Solid code here, read the Solid skill in full, the installed
node_modules/solid-js/CHEATSHEET.mdit points to, and the references it routes you to; for existing code, the refactor checklist. State ownership below still applies.
The Control UI and its plugin views use Solid 2 and native primitives; never add Lit or Web Awesome.
Solid route modules expose renderSolid(props) from the existing lazy page import.
The outlet mounts that renderer once and supplies live data, loaderPending, and
presented props; loader updates must preserve page-local state. Keep page
imports inside their route's component loader.
State Ownership And Async Results
- Gateway owns shared state; renderer copies = caches; views own presentation state. Reuse owning store/controller + Gateway contract for session, config, authorization decisions.
- Scope caches/requests to connection, agent, session. Before publishing: check owner + request generation; old results must not overwrite newer intent/another context.
- Optimistic updates: retain visible recovery state + reconcile with authority. Old requests must not roll back newer edits. Failed writes follow Gateway target and outcome contract, never renderer-selected fallback account/connection.
- Background updates may refresh scoped cache, never replace foreground selection/publish another context's state.
- Routes wait only for first-paint data. Each source (session usage, provider plans, credentials, catalog) loads, refreshes and retries on its own; refreshing one never reloads another.
Layout Stability
- Zero layout shift on load, navigation and data arrival: reserve space for late content, one loading boundary, loaded rows never return to skeletons, shell chrome keeps the same geometry on every route.
- Prove with a
layout-shiftPerformanceObserver at 400, 820 and 1280 px, entering from other routes, against a real isolated Gateway on the current build with real-scale data. Models and Usage also load fully in < 200 ms under the same setup.
Session Roster Refresh
src/lib/sessions/session-list-query.tsowns held-window reconciliation. Lifecycle, participants, placement, patch/send/steer, run-start/settlement/capacity, title snapshots may skip list reads only with unchanged membership, lineage, pin/owner/archive facts + nondecreasing recency. Tree events: complete access-scopedancestorSessions+ anyancestorSessionRefs; references need held row's admitted content revision. Preserve each row's generation + field receipts. Certified nested rows own facts; only explicit null clearing receipts may fill omissions from envelope.- Authoritative refreshes required: unknown rows, incomplete ancestor coverage, broad/catalog changes, Gateway-owned filters, failed reads, uncertain owner-prefix boundaries. Overlapping reads recheck later row receipts against their accepted membership; covered facts merge without trailing reads. Events never create filtered membership; only complete unfiltered active-only Current Work windows may admit certified full active rows below.
- Sidebar windows may exclude certified rows below a full recency window; owned rows must also fall below the bounded owner prefix. Owner-first overflow crossing into the shared page still needs authority. The connection's decoded row cache expands matching ancestor references without advancing wire baselines; evicted or mismatched references retain authoritative refresh behavior. Involving-me members need current viewer ownership or participant receipts and explicit non-hidden state; bounded participants cannot prove non-membership or admit unseen members.
- Compact rows + bounded source attribution. Enrichment flags/global-or-unknown inclusion preserve membership when kind unchanged; dashboard filters need matching
hasBoard/boardFacereceipts. Gallery pagination extends shared managed window; load full settings from descriptors on demand. Child membership: Gateway retention owner'schildOwnerSessionKeys. Parent-only events must certify complete child window; unheld ancestors need explicit exclusion or admitted reference resolved through connection row provenance. - Cached lineage re-adoption changes presentation, not managed membership. Preserve fresh descriptor/event invalidation. Apply admitted descriptor rows immediately; incomplete ancestor coverage gets one paced coordinator refresh, never read per event.
- Unfiltered History/Current Work: apply admitted rows without list refetches. History's shared row-provenance owner retains field clocks, recap updates, clearing receipts; returned lists alone own membership.
excludeSubagentsignores key-proven child exclusions only with complete access-scoped ancestor coverage; held parents/certified references still update. Missing held parents/supplied unheld ancestors need authority; named unheld parents absent from certified coverage may be invisible. Merge live facts on refresh, never replay/coalesce History packets. Missing initial membership needs catch-up; query/connection changes reset provenance. History: forward activity clocks required; preserve omitted recap enrichment; person/search filters retain authoritative refreshes. - Current Work: coalesce only consecutive full active snapshots of one generation, retaining first receipt/latest tail. Partial events, references, terminal snapshots, other identities = FIFO barriers. Complete window below limit may admit certified active row with real session ID/kind, sampled after accepted list + generation retirement/liveness clocks; preserve Gateway cron-run exclusion. Truncated/full windows, conflicting generations, partial unknown rows, ambiguous settlement, incomplete-window removals need authority.
- Current Work: apply ancestor snapshots/references via shared reconciler; pending references retain prerequisite full-row receipts. Controller caps generation-coalesced fence records at 1,000; reconciler owns independent retirement, liveness-observation, generation-authority facts. Only retirement prunes stale returned rows. Fresh certified full rows may resolve older clocked liveness; unclocked observations/conflicting generations need list read. Query/connection changes clear records. Authoritative lists clear uncertainty + covered retirements before pending replay, preserving later retirements. Saturation blocks unseen admission until authoritative read restores bounded state.
- Healthy applied roster row traffic does not schedule a fallback list read. Activity retains its 60-second fallback for whole-query people/pulse facets.
src/lib/sessions/event-refresh-coordinator.tsowns pacing + pending/trailing invalidation: sample four-to-five-second collection window once when armed; events cannot postpone it. After automatic refresh: wait three times its duration, bounded to five–15 seconds. - Accepted local creates refresh observed list membership independently of primary reads/bootstrap. Remote create events use coordinator collection/backoff with other invalidations; the Gateway still owns owner/involvement/search filtering. Retain visibility, bootstrap admission, and queued navigation ownership.
- Explicit refresh, filter/agent changes, reconnects, foreground replacement bypass backoff + absorb pending invalidation. Recheck visibility/current intent after background admission; hidden pages retain one catch-up until visible.
Reload Performance
- Reload cost is main-thread render/reconcile triggered per Gateway message; JSON parse and transport are negligible. Measured no win or regressions (2026-10-15, Team-scale bench, quiet AWS, ≥7 interleaved pairs): socket worker/SharedWorker, delivery scheduling/chunking, batched boot RPC, V8 compile hints/chunk sizing, cached DOM shell replay. WebSocket permessage-deflate saves bytes on slow links, not render time. Retry only with new evidence.
- Cut work at its owner: memoize values read per item (
createMemo), render reused UI as components rather than helper calls, keep row identity through placement/history/live updates, check cheap state before reading layout. - Measure with
scripts/bench-control-ui-cold-load.ts(long-task and render-pass probes) over several untraced runs; single DevTools traces inflate timing. Confirm the hot function with--cpu-profilefirst; never mix profiled and unprofiled timings.
i18n Rules
- Foreign
src/i18n/locales/*.ts= stable source-owned lazy adapters; translations from canonical groupedsrc/i18n/.i18n/*.tm.jsonl. Never hand-edit translation memory, locale/fallback metadata unless targeted generated-output fix requested. - English:
src/i18n/locales/en.ts, staticen-agents.ts, lazyen-*.tsregistrars.scripts/lib/control-ui-i18n-catalog.tsowns ordered composition + raw source hashes for generation, verification, Vite; reads.catalogdata without runtime registration. Wiring owners:scripts/control-ui-i18n.ts,scripts/lib/control-ui-i18n-sync-plan.ts,ui/config/control-ui-locales.ts,ui/src/i18n/lib/{types,registry}.ts. - Standalone reader English:
src/shared/public-session-copy.ts(thepublicReadernamespace in the catalog owner above).scripts/lib/public-session-locales.mtsprojects reader-only dictionaries from canonical memory into Gateway builds; source execution and untranslated keys use English. No runtime filesystem reads or separate foreign reader catalogs. src/shared/control-ui-locale.tsowns supported locales, ordered browser-language matching, and direction for UI and public reader; UI registry owns only lazy imports.- Register lazy English synchronously at each consumer, including Settings search before page load. Keep startup/shared copy eager; preserve shared
en+ sibling namespaces. Retain empty subtree anchors when extraction changes flattened order/grouped memory aliases. Never import host catalog owner into runtime. - Source PRs: update English/adapters/wiring, run keyless
pnpm ui:i18n:baseline, commit changed raw-copy baseline. Exclude fallback/locale metadata + translation memory: CI rejects mixed diffs except canonicalrelease/YYYY.M.PATCHbranches or detected complete canonical-memory migrations. - Deterministic keyless
pnpm ui:i18n:verify: English shape, runtime wiring, raw-copy drift in lint/changed-check UI. Foreign parity: post-merge bot + strict generated-output gate. - Foreign drift: the
control-ui-locale-refreshworkflow or release prep fixes it; never translate by hand or merge generated locale output.
CSS / Template Linting
pnpm lint: Solid 2 oxlint rules onui/**/*.tsxand TypeScript helpers insrc/lib/reactive/,src/components/solid/, andsrc/test-helpers/; plain domain owners keep their own contracts. Follow the Solid idioms for split effects, tracking, and lifecycle.tools/solid-lintisolates plugin tooling dependencies; corpus:test/scripts/oxlint-solid.test.ts.pnpm lint:ui:styles(included in lint):ui/srcstylesheets viaconfig/stylelint.config.mjs. Stylelint owns error rules; oxfmt owns formatting.
Stylesheet Policy
:has()limits: stylelint'sselector-disallowed-listenforces them on raw selectors (config comments say why). Apply the same limits by hand to nested&selectors, which stylelint cannot resolve.- New-tab links/controls: pointer cursors; state-changing controls: default arrow.
- Colors: use
src/styles/base.csstokens. main.runtime.tsinjectscomponents/kbd.cssdocument-wide; renderers never import it. Never JS-import a sheetstyles.cssalready ships from a lazy module: the build copies it into that chunk (catalog bytes) and re-applies it late in the cascade. Resolve cascade ties by specificity, not duplicate loading.- Breakpoints: stylelint's allowed list owns the ladder; add a rung only in config, with a comment.
node --import ./scripts/tsx.mjs scripts/audit-control-ui-dead-css.mtsadvisory. Verify selectors before deleting; extend dynamic-stem detection, not allowlist.- Nest CSS only while rewriting section; no conversion sweeps.
- No
@layer: shared light-DOM CSS depends on import order/specificity + lazy page CSS. Reconsider only with computed-style parity across all routes on mocked dev server.
Modal Completion Actions
- Place workflow completion actions last in
<openclaw-modal-actions>, after content, status and validation errors. Inside it, order dismissive and secondary buttons (Cancel, Close, Keep, Back, Retry) first and the primary or confirming action last, so the action sits at the trailing edge; destructive confirms follow the same order. The native modal stylesheet owns right alignment, wrapping and label containment. Keep submit buttons inside their native form; no renderer or custom-element registration is needed. Caller styles own spacing, not competing alignment or mobile full-width rules. Header X/Expand and field-local controls are not completion actions. Scrollable panels respect--openclaw-modal-height-limitso the footer stays reachable. Set the intended width with--openclaw-modal-widthon the native host and let child panels fill the shell instead of imposing a wider independent width.
Gateway Coupling
- UI/Gateway ship as one install/version. Never older-Gateway method fallbacks/version-conditional UI behavior.
isGatewayMethodAdvertisedonly gates config/plugin-dependent features. - Handshake rejects Gateway-served same-origin skew. Exempt
pnpm ui:dev, customgateway.controlUi.root, cross-origin/connection-settings dialing remain unsupported for mismatch: no compat, visible failure at first missing method. Rejection at connect = separate server-owned product change.
Build Chunking
- Generated
config/control-ui-boot-modules.jsonrecords ready/new+/chatcaptures: fetched modules reachable from HTML/requested dynamic entries, static imports, dynamic imports resolving into fetched chunks. Keep route-exclusive/sharedcontrol-ui-boot-*groups separate inconfig/control-ui-chunking.ts; co-located chat-only code must stay out of New Session.entrieslists requested dynamic entries;config/control-ui-boot-preloads.tsfollows static dependencies into inert route preload templates activated by Gateway. CSS hints preload bytes without changing insertion order. - Material boot-path changes:
pnpm ui:boot-manifest:gen, thenpnpm ui:buildto verify grouped output. Generation: temporary build with measured groups disabled/inactive templates, preventing stale-capture feedback. Never hand-edit manifest.
Live Verification
- Gateway serves
dist/control-ui; source edits needpnpm ui:build. Before trusting live result: verify served/assets/index-*.jshash changed.
Visual Proof
- Large design changes: run the UI stress test.
- Mock/E2E harnesses default to
communityInvite: false; Community card scenarios opt in withcommunityInvite: true. Capture the current invitation artwork and dismissed state with synthetic content across the selected theme modes, exercising the real dismiss action for persistence proof.
Trending
Less talk lately.about the whole repository
Who's talking about openclaw/openclaw
- agentskills/agentskills“Proposal: include a standard folder where agent skills should be”GitHub · Dec 19, 2025 · 270 reactions
- @sungkim.bsky.social“OpenClaw (formerly Moltbot, formerly Clawdbot) Website: openclaw.ai Repo: github.com/openclaw/ope...”Bluesky · Jan 30, 2026 · 17 likes
- NixOS/nixpkgs“openclaw: init at 2026.2.26”GitHub · Jan 30, 2026 · 13 reactions
- NousResearch/hermes-agent“[Feature]: Optional Cursor Models billing path via standalone SDK plugin (not in-tree)”GitHub · Jul 23, 2026 · 9 reactions
- @midu.dev“¡Nuevo cambio de nombre de Clawdbot! Clawd → Moltbot → OpenClaw Parece que ya el cambio definitivo. Ya …”Bluesky · Jan 30, 2026 · 8 likes
The biggest 5 of 92 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 92
Talked about on Bluesky, GitHub, the web and Hacker News (92 times).
On Bluesky · 48
- Jan 30, 2026OpenClaw (formerly Moltbot, formerly Clawdbot) Website: openclaw.ai Repo: github.com/openclaw/ope... — @sungkim.bsky.social17 likes and reposts · 1 reply
- Jan 30, 2026¡Nuevo cambio de nombre de Clawdbot! Clawd → Moltbot → OpenClaw Parece que ya el cambio definitivo. Ya tiene 100.000 estrellas en GitHub: →… — @midu.dev8 likes and reposts
- Aug 25, 2026🔥 Hot Repo! 🔥 (100+ new stars) 📦 openclaw / openclaw ⭐ 387,303 (+160) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social2 likes and reposts
- Aug 24, 2026🔥 Hot Repo! 🔥 (100+ new stars) 📦 openclaw / openclaw ⭐ 387,303 (+160) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending.bsky.social2 likes and reposts
- Jul 19, 2026🔥 Hot Repo! 🔥 (100+ new stars) 📦 openclaw / openclaw ⭐ 383,452 (+155) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social2 likes and reposts
43 more on Bluesky
- Jul 14, 2026🚀 Skyrocketing! 🚀 (200+ new stars) 📦 openclaw / openclaw ⭐ 382,900 (+208) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social2 likes and reposts · 1 reply
- May 23, 2026🧠 OpenClaw provides an open-source personal AI assistant that runs across multiple operating systems and platforms. The tool enables users… — @beyondthecode.bsky.social2 likes and reposts · 1 reply
- Mar 8, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 openclaw / openclaw ⭐ 278,291 (+4,777) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending.bsky.social2 likes and reposts · 2 replies
- Feb 19, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 openclaw / openclaw ⭐ 210,264 (+3,384) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending.bsky.social2 likes and reposts · 1 reply
- Feb 15, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 openclaw / openclaw ⭐ 195,545 (+2,758) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending.bsky.social2 likes and reposts · 1 reply
- Jan 30, 2026Clawdbot を3日前から耳にするようになりました。昨日はポッドキャストで聞き、会社で同僚も話していました。名前が Claudeに似ているので Anthropic から苦情があり、昨日の時点では Moltbot に変更されていたのですが、Openclaw… — @gakuueda.bsky.social2 likes and reposts
- Oct 30, 2026🔥 Hot Repo! 🔥 (100+ new stars) 📦 openclaw / openclaw ⭐ 393,429 (+149) 🗒 TypeScript The AI that really does things. Any OS. Any… — @github-trending-js.bsky.social1 likes and repost
- Oct 11, 2026🔥 Hot Repo! 🔥 (100+ new stars) 📦 openclaw / openclaw ⭐ 391,669 (+150) 🗒 TypeScript The AI that really does things. Any OS. Any… — @github-trending-js.bsky.social1 likes and repost
- Sep 30, 2026🔥 Hot Repo! 🔥 (100+ new stars) 📦 openclaw / openclaw ⭐ 390,829 (+136) 🗒 TypeScript The AI that really does things. Any OS. Any… — @github-trending-js.bsky.social1 likes and repost
- Sep 30, 2026今日のGitHubトレンド openclaw/openclaw OpenClawは、ユーザー自身のコンピュータで動作するオープンソースのAIアシスタントです。 DiscordやSlackなどの多様なチャットツールや各種OSのネイティブアプリで利用可能です。… — @dailygithubtrends.bsky.social1 likes and repost
- Sep 25, 2026🔥 Hot Repo! 🔥 (100+ new stars) 📦 openclaw / openclaw ⭐ 390,475 (+158) 🗒 TypeScript The AI that really does things. Any OS. Any… — @github-trending-js.bsky.social1 likes and repost
- Aug 9, 2026🔥 Hot Repo! 🔥 (100+ new stars) 📦 openclaw / openclaw ⭐ 385,644 (+170) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social1 likes and repost
- Jul 2, 2026🚀 Skyrocketing! 🚀 (200+ new stars) 📦 openclaw / openclaw ⭐ 381,420 (+240) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social1 likes and repost · 1 reply
- Jun 29, 2026OpenClaw (~380k stars) is a self-hosted personal AI assistant that answers on ~two dozen chat apps you already use, with voice and a live… — @agentpalisade.bsky.social1 likes and repost
- May 6, 2026Meta building a competitor to github.com/openclaw/ope... — @ngmi.co1 likes and repost · 1 reply
- Apr 26, 2026🎉 Celebrating! 🎉 (500+ new stars) 📦 openclaw / openclaw ⭐ 364,176 (+620) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending.bsky.social1 likes and repost · 1 reply
- Apr 8, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 openclaw / openclaw ⭐ 350,770 (+1,361) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social1 likes and repost · 2 replies
- Mar 22, 2026This GitHub repo went from 9K to 178K ⭐ in 60 days 🤯 github.com/openclaw/openclaw 18x faster than Kubernetes — fastest repo EVER 🔥… — @braneai.bsky.socialsays it tested it1 likes and repost
- Mar 11, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 openclaw / openclaw ⭐ 302,868 (+6,649) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social1 likes and repost · 1 reply
- Mar 7, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 openclaw / openclaw ⭐ 274,321 (+4,862) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social1 likes and repost · 1 reply
- Mar 6, 2026github.com/openclaw/ope... — @nutz.club1 likes and repost
- Mar 3, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 openclaw / openclaw ⭐ 252,164 (+6,312) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social1 likes and repost · 1 reply
- Feb 19, 2026今日のGitHubトレンド openclaw/openclaw OpenClawは、個人のデバイスで動作するAIアシスタントです。 WhatsAppやSlackなど、既存のチャネルを通じて応答し、音声入力やCanvas操作も可能です。… — @dailygithubtrends.bsky.social1 likes and repost
- Feb 17, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 openclaw / openclaw ⭐ 203,722 (+4,201) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social1 likes and repost · 2 replies
- Feb 13, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 openclaw / openclaw ⭐ 190,541 (+3,209) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social1 likes and repost · 1 reply
- Feb 5, 2026Running my own AI assistant on a Raspberry Pi using OpenClaw. Open source, self-hosted, connects to Telegram/Discord. What I like: I can… — @oz.akan.io1 likes and repost
- Feb 4, 2026github.com/openclaw/ope... — @tomyear.bsky.social1 likes and repost
- Feb 4, 2026got openclaw running, still surprised about it can do https://github.com/openclaw/openclaw #ai #opensource — @hapee.fosstodon.org.ap.brid.gy1 likes and repost
- Feb 3, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 openclaw / openclaw ⭐ 153,998 (+10,726) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social1 likes and repost · 1 reply
- Jan 31, 2026I have spent all day playing with openclaw when I really ought to have been doing something else. It's a fascinating bit of software and… — @doug.winter.cx1 likes and repost · 1 reply
- Jan 30, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 openclaw / openclaw ⭐ 107,151 (+16,338) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending.bsky.social1 likes and repost · 1 reply
- Jan 30, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 openclaw / openclaw ⭐ 107,153 (+16,338) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social1 likes and repost · 1 reply
- Oct 20, 2026🎉 Celebrating! 🎉 (500+ new stars) 📦 openclaw / openclaw ⭐ 392,944 (+568) 🗒 TypeScript The AI that really does things. Any OS. Any… — @github-trending-js.bsky.social0 likes and reposts · 1 reply
- Sep 2, 2026🚀 Skyrocketing! 🚀 (200+ new stars) 📦 openclaw / openclaw ⭐ 388,451 (+323) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social0 likes and reposts · 1 reply
- Jul 27, 2026🚀 Skyrocketing! 🚀 (200+ new stars) 📦 openclaw / openclaw ⭐ 384,298 (+208) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social0 likes and reposts · 1 reply
- Jul 2, 2026READMEと公式docsで確認できた範囲だと、OpenClaw は“スマホ単体の万能助手”より「自分の端末群で動かす個人用AI」です。Androidアプリも companion node で、running Gateway が必須。導入も Node.js… — @mint-echosphere.bsky.social0 likes and reposts · 1 reply
- Jun 8, 2026I don't think the AI agent era is coming. I think it's already here and we're still catching up. OpenClaw (free):… — @fatcat77.bsky.social0 likes and reposts · 1 reply
- Jun 5, 2026🚀 Skyrocketing! 🚀 (200+ new stars) 📦 openclaw / openclaw ⭐ 377,015 (+344) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social0 likes and reposts · 1 reply
- Apr 26, 2026🎉 Celebrating! 🎉 (500+ new stars) 📦 openclaw / openclaw ⭐ 364,176 (+620) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social0 likes and reposts · 1 reply
- Feb 26, 2026💎 Hidden Gem! 💎 (1000+ new stars) 📦 openclaw / openclaw ⭐ 231,605 (+4,074) 🗒 TypeScript Your own personal AI assistant. Any OS. Any… — @github-trending-js.bsky.social0 likes and reposts · 3 replies
- Feb 17, 2026今日のGitHubトレンド openclaw/openclaw OpenClawは、個人のデバイス上で動作するAIアシスタントです。 WhatsAppやSlackなど、既存のチャネルを通じて応答し、音声入力やCanvas操作も可能です。… — @dailygithubtrends.bsky.social0 likes and reposts · 2 replies
- Feb 2, 2026Anyone experimented with the #OSS #OpenClaw, the "personal #AI assistant", yet? I watched the @heise.de video (in German). That is scary,… — @hillert.bsky.social0 likes and reposts · 1 reply
- Jan 30, 2026Reading though the source code for github.com/openclaw/ope... / MoltBot (formerly ClawdBot), and maybe the thing about specifying skills… — @danlyke.bsky.social0 likes and reposts · 1 reply
On GitHub · 17
- Dec 19, 2025Proposal: include a standard folder where agent skills should be — agentskills/agentskills270 reactions · 130 comments
- Jan 30, 2026openclaw: init at 2026.2.26 — NixOS/nixpkgs13 reactions · 14 comments
- Jul 23, 2026[Feature]: Optional Cursor Models billing path via standalone SDK plugin (not in-tree) — NousResearch/hermes-agent9 reactions · 1 comment
- May 4, 2026[v2026.5.3-1] [OpenClaw] Is it stable? — exisz/IsItStable7 reactions · 3 comments
- Apr 14, 2026Feature: Single-Daemon Multi-Agent with Per-Topic Workspace & Memory Isolation — NousResearch/hermes-agent7 reactions · 12 comments
12 more on GitHub
- May 3, 2026[v2026.5.2] [OpenClaw] Is it stable? — exisz/IsItStable6 reactions · 2 comments
- Mar 3, 2026OpenClaw 2026.3.2 版本安装插件失败 — sunnoy/openclaw-plugin-wecom6 reactions · 5 comments
- Jul 7, 2026feat(mobile): native Android app for Hermes Agent (companion to gateway) — NousResearch/hermes-agent5 reactions · 3 comments
- Mar 23, 2026model/parsers: Close think block if tool block starts in Qwen3.5 — ollama/ollama5 reactions · 2 comments
- Mar 9, 2026Channels support WeCom — RightNow-AI/openfang5 reactions · 3 comments
- Feb 23, 2026[Question] Node 24 (v137) prebuilt binary availability — discordjs/opus5 reactions
- Feb 14, 2026Add Openclaw — truenas/apps5 reactions · 2 comments
- Jul 31, 2026fix: restore automatic high-confidence OpenClaw bug repairs — openclaw/clawsweeper3 reactions · 13 comments
- Jun 20, 2026RFC: multi-slot memory role architecture — openclaw/rfcs3 reactions · 1 comment
- May 21, 2026feat(runtimes): add OpenClaw ACP adapter — nexu-io/open-design3 reactions · 9 comments
- May 7, 2026Align OpenClaw 2026.5 compatibility — joshuaswarren/remnic3 reactions
- May 6, 2026[Responses API] Fold developer-role input messages into instructions — vllm-project/vllm3 reactions · 8 comments
On the web · 15
- Apr 6, 2026The Complete Guide to OpenClaw: From Installation to Security Settings [2026 Latest Edition]|HIROKI — note.com
- Mar 31, 2026OpenClaw setup guide: Build your personal AI agent — lennysnewsletter.com
- Mar 19, 2026OpenClaw Review: Building Multi-Agent AI Systems in 2026 — dev.to
- Mar 10, 2026OpenClaw: The Complete Guide (Setup, Features, Costs, Use Cases & Security) | by Aiheralduae — medium.com
- Mar 2, 2026OpenClaw Review: Truly Agentic AI or “AI Employee” Hype? — ai-consultant-norwich.co.uk
10 more on the web
- Feb 22, 2026All you need to know about 🦞 OpenClaw — dev.to
- Feb 22, 2026How OpenClaw Actually Works. AI Agent | by JIN | JIN System Architect — medium.com
- Feb 21, 2026OpenClaw Review 2026: Honest Assessment After Daily Use — computertech.co
- Feb 11, 2026My experience with OpenClaw 🦞 - by Luca Rossi — refactoring.fm
- Feb 10, 2026Openclaw the best ai assistant — medium.com
- Feb 5, 2026Is OpenClaw Worth the Hype? I Spent 10 Days Finding Out — aimaker.substack.com
- Feb 2, 2026OpenClaw (Formerly ClawdBot & Moltbot): A Complete Overview of this New AI Assistant & Practical Guide | Fello AI — felloai.com
- Feb 1, 2026One Week Later with OpenClaw (prev. ClawdBot, prev. MoltBot): A Product Designer's Honest Take — nervegna.substack.com
- Jan 30, 2026Clawdbot → Moltbot → OpenClaw ≠ магия: честный гайд по приручению AI-ассистента / Хабр — habr.com
- Jan 30, 2026OpenClaw UX Review: Is Local Agentic AI Ready for ... — uxwritinghub.com
On Hacker News · 12
- Feb 9, 2026Added OTEL Observability to OpenClaw agents full GenAI spec support6 points · 2 comments
- Feb 5, 2026Show HN: I've been running OpenClaw on a $640 Mac Mini for a week. Honest report6 points · 2 comments
- Jan 31, 2026OpenClaw 2026.1.30 Is Live3 points · 1 comment
- Sep 8, 2026OpenClaw Is Open Source2 points
- May 23, 2026OpenClaw: Own Personal AI Assistant. Any OS. Any Platform2 points
7 more on Hacker News
- Feb 18, 2026Show HN: OpenClaw – Open-source personal AI agent that lives on your machine2 points · 3 comments
- Oct 31, 2026An AI agent read a Shift_JIS page as 208,953 replacement characters1 point
- Sep 30, 2026OpenClaw: Test Audit Skill1 point
- Sep 4, 2026The AI That Does Things. Any OS. Any Platform1 point
- Feb 7, 2026PR to support XMPP channels in OpenClaw1 point
- Feb 2, 2026OpenClaw1 point · 2 comments
- Jan 31, 20261-Click RCE in ClawdBot (Openclaw/Moltbot)1 point
Other versions2 projects use a version of this.
Word for word · 2
- clawdbot/clawdbot★ 394k100% same
- steipete/clawdis★ 394k100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 28,693 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository109 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- extensions/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- test/AGENTS.mdAGENTS.md
- agent-transcriptSkill
- auto-qaSkill
- autoreviewSkill
- channel-message-flowsSkill
- clawdtributorSkill
- claw-scoreSkill
- clawsweeperSkill
- control-ui-e2eSkill
- crabboxSkill
- discord-clawdSkill
- discord-e2eSkill
- discord-user-postSkill
- discrawlSkill
- gitcrawlSkill
- graincrawlSkill
- notcrawlSkill
- openclaw-changelog-updateSkill
- openclaw-ci-limitsSkill
- openclaw-debuggingSkill
- openclaw-docker-e2e-authoringSkill
- openclaw-ghsa-maintainerSkill
- openclaw-live-updaterSkill
- openclaw-parallels-smokeSkill
- openclaw-performanceSkill
- openclaw-pr-maintainerSkill
- openclaw-qa-testingSkill
- openclaw-refactor-docsSkill
- openclaw-release-validationSkill
- openclaw-repair-sweepSkill
- openclaw-secret-scanning-maintainerSkill
- openclaw-test-heap-leaksSkill
- openclaw-testingSkill
- openclaw-test-performanceSkill
- openclaw-updateSkill
- parallels-discord-roundtripSkill
- plugin-sdk-impactSkill
- proof-videoSkill
- prototype-openclaw-tuiSkill
- pr-simplifySkill
- release-openclaw-announcementSkill
- release-openclaw-ciSkill
- release-openclaw-macSkill
- release-openclaw-maintainerSkill
- release-openclaw-plugin-testingSkill
- security-triageSkill
- slack-e2eSkill
- slacrawlSkill
- solidSkill
- tag-duplicate-prs-issuesSkill
- technical-documentationSkill
- telegram-e2e-userbotSkill
- test-auditSkill
- update-team-serverSkill
- verify-releaseSkill
- 1passwordSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

