eliza
AGENTS.md20k starsChanged 26 days agoMITView on GitHub
Monorepo for the Eliza agent runtime, application, cloud services, native bridges, benchmarks, and first-party plugins. Read CONTRIBUTING.md and the owning package's README.md before editing; manifests and source are authoritative. This root file is the only repository agent guide. Do not add nested AGENTS.md files. [!IMPORTANT] The contribution rules are required for all issues and PRs. Report real bugs or missing approved MVP requirements. Link the PRD and MVP plan. Do not add features outside that scope. Human maintainers must discuss…
We split this AGENTS.md into the rules it gives an agent
15 rules. About 0 are common, 11 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Prefer cleanup, removal, and reuse.
- Distinctive: line 26
Add new types or code only when necessary.
- Distinctive: line 28
Do not create work for minor points with no useful effect, unnecessary tests, defensive code, validation, or truncation.
- Distinctive: line 31
Use existing tests. Avoid new unit tests, mock-only proof, and tests that repeat the implementation.
- Distinctive: line 33
Every UI PR must include an uploaded MP4 explainer and walkthrough with video evidence of the complete user flow, plus detailed steps to …
- Distinctive: line 35
Write all issues and PRs in ASD-STE100 Simplified Technical English.
- Distinctive: line 38
Use real LLM calls for evidence.
- Distinctive: line 44
Use pinned Bun 1.4.2 and Node 24.15.0, ESM, and the repository's Biome config.
- Distinctive: line 45
Keep core independent of hosts.
- Very specific: line 49
Use the structured logger and runtime.reportError for runtime diagnostics.
- Distinctive: line 50
Keep model-facing context and recorded training data complete.
- Distinctive: line 53
Use the existing scheduler, entity/relationship stores, and content-addressed media store.
- Very specific: line 55
Keep READMEs and agent guides short.
- Very specific: line 58
Use packages/scripts/lib/test-output.ts for stable output paths.
- Very specific: line 59
Verify changed behavior with the owning package's tests, typecheck, and lint, then bun run verify.
≈ “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
elizaOS
Monorepo for the Eliza agent runtime, application, cloud services, native
bridges, benchmarks, and first-party plugins. Read CONTRIBUTING.md
and the owning package's README.md before editing; manifests and source are
authoritative. This root file is the only repository agent guide. Do not add
nested AGENTS.md files.
[!IMPORTANT] The contribution rules are required for all issues and PRs. Report real bugs or missing approved MVP requirements. Link the PRD and MVP plan. Do not add features outside that scope. Human maintainers must discuss and approve new features, then add them to the PRD and MVP plan before implementation issues or PRs are opened. Maintainers will close unnecessary work and apply contributor penalties.
- Human-only issue creation: Outside contributors must personally write the issue title and body and submit the issue by hand on the GitHub website. Agents must not write or create issues for contributors. Do not use an API, CLI, browser automation, or another agent to submit an issue. Human approval of an agent-written issue does not meet this rule. An agent that finds a problem must report it privately to the human in the current work session; the human decides whether to write and submit an issue.
- Prove a useful improvement with before-and-after behavior or relevant scores. Prefer cleanup, removal, and reuse. Combine duplicate types and functions. Add new types or code only when necessary. Explain the research, alternatives, and reason for the chosen implementation.
- Do not create work for minor points with no useful effect, unnecessary tests, defensive code, validation, or truncation. Preserve required safety boundaries.
- Validate real behavior end to end and attach results for the reviewed commit. Use existing tests. Avoid new unit tests, mock-only proof, and tests that repeat the implementation. For documentation-only work, check the text and links.
- Every UI PR must include an uploaded MP4 explainer and walkthrough with video evidence of the complete user flow, plus detailed steps to test the change.
- Write all issues and PRs in ASD-STE100 Simplified Technical English. Use short, direct sentences, explain technical terms, and write for a non-technical reader.
- Slop bounty work: star and fork the repository first and work from the fork. Use real LLM calls for evidence. Make no UI changes except broken-flow fixes with before-and-after video. Test in more than one agent client and record each client, version, provider, and model. Rules, environment variables, and the evidence checklist: Slop bounty contributions.
- Preserve unrelated changes in this shared working tree.
- Use pinned Bun 1.4.2 and Node 24.15.0, ESM, and the repository's Biome config.
- Keep core independent of hosts; hosts compose assistant behavior, storage, and model providers. Validate untrusted input at boundaries.
- Preserve authorization, tenant isolation, cancellation, and effect receipts.
Throw typed errors; never fabricate success or hide failures as empty data.
Use the structured logger and
runtime.reportErrorfor runtime diagnostics. - Keep model-facing context and recorded training data complete. Preserve the existing authorized source-selection/restoration contract; do not add silent truncation, summaries, or recency limits. Reject hard size limits explicitly.
- Use the existing scheduler, entity/relationship stores, and content-addressed media store. Do not introduce parallel ownership or bypass SSRF guards.
- Keep READMEs and agent guides short. Retain other Markdown only when consumed
by runtime, build, tests, publishing, or required attribution. Generated
reports belong in ignored repository-root
test-results/, with one leaf per producer. Usepackages/scripts/lib/test-output.tsfor stable output paths. - Verify changed behavior with the owning package's tests, typecheck, and lint,
then
bun run verify. Validate documentation links for docs-only changes. UI changes require the app visual audit and desktop/mobile inspection. - Submit changes through a PR against
develop. Report vulnerabilities privately through GitHub Security Advisories. The community plugin registry is retired; first-party catalog data lives inpackages/core/src/catalog/.
Getting started, build, test, and benchmark commands: README.md.
Design inventories are advisory; do not gate builds on saved component counts, story percentages, or expired review metadata.
Trending
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Who's talking about elizaOS/eliza
- anush008/tokenizers“Add support for linux arm64”GitHub · Jan 17, 2025 · 13 reactions
- @geeknik.bsky.social“Autonomous agents are here to eat your job, your cat, and your existential dread. 𝚎𝚕𝚒𝚣𝚊𝙾𝚂: where AI …”Bluesky · Jan 4, 2025 · 4 likes
- @testingcatalog.com“Interesting how these social platforms are slowly becoming a communication channel for AI agents. - AI …”Bluesky · Dec 30, 2024 · 3 likes
- A Hacker News story“Show HN: ElizaOS 1.0 - Powerful and useful multi-agent framework in Typescript”Hacker News · Jul 12, 2025 · 2 points
- @tsunderella.moe“it can be done, and likely has”Bluesky · Feb 22, 2025 · 2 likes
The biggest 5 of 66 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 66
Talked about on GitHub, Bluesky, Hacker News and the web (66 times).
On GitHub · 50
- Jan 17, 2025Add support for linux arm64 — anush008/tokenizers13 reactions · 1 comment
- Mar 20, 2026feat: simplified onboarding, UI redesign, knowledge image support — milady-ai/milady1 reaction · 4 comments
- Oct 28, 2026bounty digest 2026-10-28 — airdropia/earn-ops0 reactions · 1 comment
- Oct 28, 2026Preserve clean Alpha integration, Notes saves and native enrollment — eliza-research/alphaphone0 reactions · 2 comments
- Oct 27, 2026bounty digest 2026-10-27 — airdropia/earn-ops0 reactions
45 more on GitHub
- Oct 26, 2026fix: skill drift detected 2026-10-26 — ItachiDevv/elizaos-skill0 reactions
- Oct 26, 2026bounty digest 2026-10-26 — airdropia/earn-ops0 reactions · 2 comments
- Oct 25, 2026bounty digest 2026-10-25 — airdropia/earn-ops0 reactions
- Oct 24, 2026radar: revalidate doc 205 (no-change) — bettercallzaal/ZAOOS0 reactions · 3 comments
- Oct 24, 2026bounty digest 2026-10-24 — airdropia/earn-ops0 reactions
- Oct 23, 2026bounty digest 2026-10-23 — airdropia/earn-ops0 reactions · 1 comment
- Oct 22, 2026bounty digest 2026-10-22 — airdropia/earn-ops0 reactions
- Oct 21, 2026bounty digest 2026-10-21 — airdropia/earn-ops0 reactions
- Oct 20, 2026bounty digest 2026-10-20 — airdropia/earn-ops0 reactions
- Oct 19, 2026fix: skill drift detected 2026-10-19 — ItachiDevv/elizaos-skill0 reactions
- Oct 18, 2026fix(points): zero a pre-window review that a newer snapshot excludes — SlopDotCash/slopdotcash0 reactions
- Oct 15, 2026Connect resident Maps actions to phone navigation — eliza-research/alphaphone0 reactions
- Oct 15, 2026Record current-pin native voice candidate execution — eliza-research/alphaphone0 reactions
- Oct 14, 2026Wire Maps to the Eliza Cloud Maps service routes (draft, depends on elizaOS/eliza#36185) — eliza-research/alphaphone0 reactions · 1 comment
- Oct 13, 2026Network OAuth SMS blocked: Twilio account authentication fails with 401 / 20003 — eliza-research/thenetwork0 reactions
- Oct 12, 2026fix: skill drift detected 2026-10-12 — ItachiDevv/elizaos-skill0 reactions
- Oct 10, 2026Publish Eliza/SAK/GOAT plugins + upstream proposals; Musebook/ClawPump drafts — fxams/crew0 reactions
- Oct 10, 2026Consume merged upstream password manager and retire local patch — eliza-research/alphaphone0 reactions
- Oct 10, 2026Deliver canonical onboarding while unknown-age accounts stay private — eliza-research/thenetwork0 reactions
- Oct 10, 2026TODO: Complete final MVP qualification against approved policies — eliza-research/alphaphone0 reactions · 9 comments
- Oct 10, 2026TODO: Deliver and qualify the approved AOSP MVP image — eliza-research/alphaphone0 reactions · 5 comments
- Oct 10, 2026Retire phone pairing for the on-device agent — eliza-research/alphaphone0 reactions · 1 comment
- Oct 8, 2026feat(app): connect native Notes, Calendar and brief source flows — eliza-research/alphaphone0 reactions
- Oct 8, 2026chore: consume reviewed Eliza runtime and notification fixes — eliza-research/alphaphone0 reactions
- Oct 5, 2026agent-skills.github.elizaos.eliza: 14 → 14-unstable-2026-10-05 — sudosubin/agents.nix0 reactions
- Oct 5, 2026fix(inbox): page chat history past the agent's own replies — hermesagent270-commits/eliza0 reactions
- Oct 5, 2026fix(inbox): open iMessage links from the stored chat id — hermesagent270-commits/eliza0 reactions
- Oct 5, 2026Remove retired native qualification tools — eliza-research/alphaphone0 reactions
- Oct 5, 2026fix: skill drift detected 2026-10-05 — ItachiDevv/elizaos-skill0 reactions
- Oct 3, 2026agent-skills.github.elizaos.eliza: init at 14 — sudosubin/agents.nix0 reactions
- Sep 30, 2026Request maintainer evaluation: fadhelcarlos PR elizaOS/eliza#32908 incorporated into #32909 — SlopDotCash/slopdotcash0 reactions · 4 comments
- Sep 29, 2026Remove hijacked walletOS link and fix links flagged by the weekly check — Skelt24/awesome-solana-ecosystem0 reactions
- Sep 28, 2026fix: skill drift detected 2026-09-28 — ItachiDevv/elizaos-skill0 reactions
- Sep 28, 2026Broken links report — Li-Evan/awesome-jev0 reactions
- Sep 21, 2026fix: skill drift detected 2026-09-21 — ItachiDevv/elizaos-skill0 reactions
- Sep 14, 2026fix: skill drift detected 2026-09-14 — ItachiDevv/elizaos-skill0 reactions
- Aug 31, 2026fix: skill drift detected 2026-08-31 — ItachiDevv/elizaos-skill0 reactions
- Aug 29, 2026[repo] elizaOS/eliza — lucas-albers-lz4/sre-ai-llm-work0 reactions · 2 comments
- Aug 24, 2026fix: skill drift detected 2026-08-24 — ItachiDevv/elizaos-skill0 reactions
- Aug 24, 2026Request maintainer evaluation: superseded Neutize PR elizaOS/eliza#25803 — SlopDotCash/slopdotcash0 reactions · 1 comment
- Aug 23, 2026Request maintainer evaluation: GG100-eng review on elizaOS/eliza#24433 — SlopDotCash/slopdotcash0 reactions
- Aug 22, 2026fix(deploy): add protected staging migration gate before develop rollout — Steward-Fi/steward0 reactions
- Aug 21, 2026Request maintainer evaluation: Neutize reviews on elizaOS/eliza#23362 and #23364 — SlopDotCash/slopdotcash0 reactions · 2 comments
- Aug 20, 2026Eliza review preflight invalidates pinned proof after repository transfer — SlopDotCash/slopdotcash0 reactions
- Aug 17, 2026fix: skill drift detected 2026-08-17 — ItachiDevv/elizaos-skill0 reactions
On Bluesky · 12
- Jan 4, 2025Autonomous agents are here to eat your job, your cat, and your existential dread. 𝚎𝚕𝚒𝚣𝚊𝙾𝚂: where AI meets chaos theory in a blender… — @geeknik.bsky.social4 likes and reposts
- Dec 30, 2024Interesting how these social platforms are slowly becoming a communication channel for AI agents. - AI agents may bring more traffic there… — @testingcatalog.com3 likes and reposts
- Feb 22, 2025it can be done, and likely has — @tsunderella.moe2 likes and reposts · 1 reply
- Feb 9, 2025📦 elizaOS / eliza ⭐ 14,147 (+49) 🗒 TypeScript Autonomous agents for everyone — @github-trending-js.bsky.social2 likes and reposts
- Jan 23, 2025🔥 Hot Repo! 🔥 (100+ new stars) 📦 elizaOS / eliza ⭐ 12,705 (+193) 🗒 TypeScript Autonomous agents for everyone — @github-trending-js.bsky.social2 likes and reposts
7 more on Bluesky
- Jan 3, 2025🎉 Celebrating! 🎉 (500+ new stars) 📦 elizaOS / eliza ⭐ 8,788 (+565) 🗒 TypeScript Autonomous agents for everyone — @github-trending.bsky.social2 likes and reposts · 1 reply
- Dec 29, 2024🔥 Hot Repo! 🔥 (100+ new stars) 📦 elizaOS / eliza ⭐ 6,394 (+123) 🗒 TypeScript Autonomous agents for everyone — @github-trending-js.bsky.social2 likes and reposts · 1 reply
- Jul 8, 2025📦 elizaOS / eliza ⭐ 16,290 (+90) 🗒 TypeScript Autonomous agents for everyone — @github-trending-js.bsky.social1 likes and repost
- Jun 16, 2025github.com/elizaOS/eliza — @ens0.me1 likes and repost · 1 reply
- Jan 27, 2025Sad tweeter meddle election github.com/elizaOS/eliza — @jungchanhsieh.bsky.social1 likes and repost
- Jan 2, 2025🚀 Skyrocketing! 🚀 (200+ new stars) 📦 elizaOS / eliza ⭐ 8,445 (+431) 🗒 TypeScript Autonomous agents for everyone — @github-trending-js.bsky.social1 likes and repost · 1 reply
- Dec 29, 2024🔥 Hot Repo! 🔥 (100+ new stars) 📦 elizaOS / eliza ⭐ 6,394 (+123) 🗒 TypeScript Autonomous agents for everyone — @github-trending.bsky.social1 likes and repost · 1 reply
On Hacker News · 3
- Jul 12, 2025Show HN: ElizaOS 1.0 - Powerful and useful multi-agent framework in Typescript2 points
- Jan 5, 2025Eliza OS – open-source AI agent framework for crypto and more2 points · 1 comment
- Jan 4, 2025ElizaOS – Powering Agents on X2 points
On the web · 1
- Jun 30, 2025Test · Issue #5315 · elizaOS/eliza — google.com
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.
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.

