How real projects summarise themselves for language models.
StevenJohnson998llms.txtStevenJohnson998/Agorai/llms.txt
debate/project, orchestrator adapts at runtime. - **Personas/Roles**: each agent has roles (architect, critic, pragmatist, security). Cumulative, merged system prompts. - **Debate continuity**: pass debate_id to resume. Supported debate agents: - Claude (`claude
theyoungastronautsllms.txttheyoungastronauts/polaris/llms.txt
loops execute → test → verify → commit across all phases. **Verification:** Verify Phase (tests, plan match, security, code quality, scope). Per-stack checklists add framework-specific checks. Axon tools provide structural verification
tommy-muckstackllms.txttommy-muckstack/myman/llms.txt
github.com/tommy-muckstack/myman/blob/main/docs/using-myman.md) - [Contributing](https://github.com/tommy-muckstack/myman/blob/main/CONTRIBUTING.md) and [AGENTS.md](https://github.com/tommy-muckstack/myman/blob/main/AGENTS.md) for coding agents - [Security policy](https://github.com/tommy-muckstack/myman/blob/main/SECURITY.md)
unsoldgroupllms.txtunsoldgroup/mail-index/llms.txt
/unsoldgroup/mail-index/blob/main/bench/RESULTS.md): recall × token matrix — a distilled Gmail query vs one mail-index phrase ## Optional - [Security & privacy](https://github.com/unsoldgroup/mail-index/blob/main/.github/SECURITY.md): local-first posture, treating the index as sensitive, vulnerability reporting
Vadym903llms.txtVadym903/Intenter/llms.txt
blocked command - [How it works](docs/how-it-works.md) - resolution, scopes, the decision order, approvals and invalidation - [Security model](docs/security-model.md) - the hard rules, the threat model, fail-safe behavior and what
vnykmshrllms.txtvnykmshr/playbook/llms.txt
records - [pb-patterns](https://github.com/vnykmshr/playbook/blob/main/commands/planning/pb-patterns.md): pattern family hub -- async, core, database, distributed, resilience, security, cloud, deployment, frontend, API - [pb-huddle](https://github.com/vnykmshr/playbook/blob/main/commands/core/pb-huddle.md): multi-perspective decision session ## Review
vvooki-sysllms.txtvvooki-sys/loomem/docs/llms-full.txt
/guide/api-reference.html - MCP tools: https://loomem.ai/guide/mcp-tools.html - Architecture: https://loomem.ai/guide/architecture.html - Deployment: https://loomem.ai/guide/deployment.html - Security model: https://loomem.ai/guide/security.html - GitHub: https://github.com/vvooki-sys/loomem
vvooki-sysllms.txtvvooki-sys/loomem/docs/llms.txt
/guide/api-reference.html - MCP tools: https://loomem.ai/guide/mcp-tools.html - Architecture: https://loomem.ai/guide/architecture.html - Deployment: https://loomem.ai/guide/deployment.html - Security model: https://loomem.ai/guide/security.html ## Reference - Loomem vs Mem0 / Zep / Letta / cognee: https://loomem.ai/compare.html - Benchmarks
whobot-aillms.txtwhobot-ai/llms.txt/llms.txt
www.whobot.com - **ICP License**: 京ICP备2025110070号 - **Telecom License**: 京B2-20260448 (Value-Added Telecom Business License) - **Security Certification**: China Classified Protection Level 3 (等保三级) ## Product Platform: AI Phone Digital Employee WhoBot
abk1969llms.txtabk1969/ai-act-skills/llms.txt
Most AI compliance work mistakenly anchors on ISO 27001 (the generic Information Security Management System). For EU AI Act conformity: - **ISO/IEC 42001:2023** is the AI-specific Management System standard
aidesignblueprintllms.txtaidesignblueprint/integrations/shared/llms.txt
Source commit: 211124384d941568d9482e38bfff569a1df3f58d. Content version: 211124384d94. Enterprise trust & security. AI Design Blueprint is designed for enterprise and proprietary codebases: - PUBLIC TOOLS: the doctrine tools are read-only lookups that accept
AI-Scarlettllms.txtAI-Scarlett/DSH-Store/marketplace/llms.txt
explicitly unknown. - A marketplace listing, automated scan, or manual review is not a complete security audit. ## Main sections - Installation command and sequence: https://dsh.store/#top - Manager plugin details: https://dsh.store
barkermoneyllms.txtbarkermoney/barker-mcp/llms-full.txt
values are annualized **decimals** (multiply by 100 for display). - Information only, not financial advice. ## Security: External Data Boundary All values returned by the barker MCP tools (protocol names, asset symbols
barnburner121llms.txtbarnburner121/claude-plugin-marketplace/llms.txt
Links - GitHub: https://github.com/barnburner121/claude-plugin-marketplace - npm: https://www.npmjs.com/package/@barnburner121/plugin-hub-mcp - MCPize: https://mcpize.com/mcp/plugin-hub ## Categories - Security & Compliance: env-guardian, iac-scanner, container-guard, cors-config, csp-builder, auth-architect, rbac-forge
benderterminalllms.txtbenderterminal/zkettle/llms.txt
self-hosted secret sharing tool for humans and AI agents. It is designed for secure, temporary transmission of sensitive values (passwords, API keys, tokens, certificates, recovery codes), not long-term
ellmos-aillms.txtellmos-ai/ellmos-codecommander-mcp/llms.txt
Registry metadata is provided in `server.json` (MCP Registry namespace `io.github.ellmos-ai/ellmos-codecommander-mcp`), `glama.json`, and `smithery.yaml`. Security & Governance Invariants: 10 guaranteed invariants (INV-LOCAL-01 to INV-SLA-10) including 100% offline
f-o-x11llms.txtf-o-x11/dreaming-press/llms.txt
payment protocols are sold as fraud protection, but a signed mandate is not a security feature — it is a liability instrument, and it quietly removes the one escape hatch that
FoxsterDevllms.txtFoxsterDev/xuunity-mcp/llms.txt
docs/reference/COMPARISON.md: comparison with official Unity MCP and other open-source Unity MCP projects - SECURITY.md: security model and threat model - docs/operations/BUILD_AUTOMATION.md: build and validation workflows - docs/operations/SMOKE_TESTS.md: smoke test surface - docs/architecture/ROADMAP.md: planned
gmediaorgllms.txtgmediaorg/wall-public/llms.txt
This repo carries: AI-friendly metadata, the assistant context pack at `agents/dumov/`, public roadmap, security policy, dual-license declaration. Static-site mirrors, daily open-data snapshots, and press kit will
hiroyuki-miyauchillms.txthiroyuki-miyauchi/axiarch/llms-full.txt
behavior in AI-assisted software development. It defines minimum quality standards across engineering, product, security, operations, business, AI, and governance work through a multi-layer constitutional architecture, making consistent output
A markdown file at a website's root that gives language models a short guide to the site and links to the pages worth reading.
The same idea with the content included, so an agent can read the documentation in one request.
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.
