best-of-Agent-Harnesses
RyanAlberts/best-of-Agent-Harnesses/llms.txt
# Best of Agent Harnesses > Hand-curated, ranked list of 188 AI agent harnesses — the
Steady2 mentions in 2 weeks
No other project uses it yet
How real projects summarise themselves for language models.
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.
RyanAlberts/best-of-Agent-Harnesses/llms.txt
# Best of Agent Harnesses > Hand-curated, ranked list of 188 AI agent harnesses — the
Steady2 mentions in 2 weeks
No other project uses it yet
arihantcodes/spectrum-ui/public/llms-full.txt
# Spectrum UI — Full Catalog > Spectrum UI is an open-source React component and block
No other project uses it yet
yuzeguitarist/Deck/llms-full.txt
Core Features - Fast keyword / regex / type search - Queue mode for multi-step paste workflows - Secure LAN clipboard sharing (AES-GCM) - Touch ID protection for sensitive data access - Semantic search
No other project uses it yet
yuzeguitarist/Deck/llms.txt
Rights Reserved - Core traits: fast search, queue mode, Touch ID protection, local-first privacy, secure LAN sharing (AES-GCM) - Notable capabilities from repo docs: semantic search, OCR text extraction, iCloud
No other project uses it yet
ealush/emoji-picker-react/llms-full.txt
# emoji-picker-react — complete documentation > Emoji picker for React: batteries included with ` `, or BYOD
No other project uses it yet
mbailey/voicemode/llms.txt
sophisticated formatting for your prose and code on GitHub with simple syntax. ## Authentication > Authenticate securely to GitHub with passwords, tokens, SSH keys, and more—and keep your account protected. - [Connect
No other project uses it yet
nucliweb/webperf-snippets/public/llms-full.txt
# WebPerf Snippets — Full Reference Tested JavaScript snippets that measure and debug web performance. Your
Steady17 mentions in 2 weeks
No other project uses it yet
LilMGenius/paperthin/llms.txt
risky input. Use when a task includes stealth, scraping, privacy, IP, policy, licensing, security, or other safety-adjacent material that could be silently dropped, over-elaborated, or needlessly diluted. Fires
No other project uses it yet
microsoft/winappCli/llms.txt
github.com/microsoft/WinAppCli/blob/main/docs/debugging.md): `winapp run` vs `create-debug-identity`, IDE setup, and debugging workflows - [Security Guidance](https://github.com/microsoft/WinAppCli/blob/main/docs/security.md): What development certificates and Developer Mode change on a machine, safe handling
Steady10 mentions in 2 weeks
No other project uses it yet
ksimback/hermes-ecosystem/llms.txt
/guide/install/vps/): The always-on server setup — sizing, Docker vs direct, and the mandatory-auth security guidance. - [The Hermes Agent Memory Guidebook](https://hermesatlas.com/guide/memory/): Kevin Simback's guide to native
No other project uses it yet
mongodb/kingfisher/docs-site/docs/llms.txt
/kingfisher/reference/project/) ## Repository - [Source](https://github.com/mongodb/kingfisher) - [Changelog](https://github.com/mongodb/kingfisher/blob/main/CHANGELOG.md) - [Contributing](https://github.com/mongodb/kingfisher/blob/main/CONTRIBUTING.md) - [Security policy](https://github.com/mongodb/kingfisher/blob/main/SECURITY.md)
peonist-ai/halogen-flash-server/llms.txt
hold a side-effecting tool call. A second pair of eyes, not a security boundary. - [Flint preview](https://raw.githubusercontent.com/peonist-ai/halogen-flash-server/main/docs/flint-preview.md): RecursiveSI's Flint on its own image tag ## Numbers - [Measured
stoolap/stoolap/llms.txt
benchmark.rs - [Benchmarks](https://github.com/stoolap/stoolap/blob/main/BENCHMARKS.md): point-in-time figures; validate on your own workload - [Security policy](https://github.com/stoolap/stoolap/blob/main/SECURITY.md) ## Notes for coding agents - Embedded only: there is no server process
No other project uses it yet
openqodex/openqodex/docs/llms.txt
Reviewer drivers](internal-reviewer-drivers.md) - [Library](library.md) - [Plumbing commands](plumbing.md) - [Privacy](privacy.md) - [Quickstart](quickstart.md) - [Scanners](scanners.md) - [Security](security.md) - [Telemetry](telemetry.md
No other project uses it yet
hoangsonww/Claude-Code-Agent-Monitor/llms.txt
source of truth for API contracts). - [Repository](https://github.com/hoangsonww/Claude-Code-Agent-Monitor): Source, issues, and discussions. - [security policy](https://github.com/hoangsonww/Claude-Code-Agent-Monitor/security/policy): Reporting vulnerabilities. - [LICENSE](https://raw.githubusercontent.com/hoangsonww/Claude-Code-Agent-Monitor/master/LICENSE): MIT license text
No other project uses it yet
DeepMyst/Mysti/llms.txt
Publishing GitHub demos](https://raw.githubusercontent.com/DeepMyst/Mysti/main/docs/media/README.md): Upload canonical native videos and verify real playback. - [Security reporting](https://raw.githubusercontent.com/DeepMyst/Mysti/main/.github/SECURITY.md): Report a vulnerability privately and understand support scope. - [Changelog](https://raw.githubusercontent.com
sirkirby/unifi-network-mcp/docs/llms.txt
command providers that keep passwords and API keys out of the client environment. - [Security policy](https://github.com/sirkirby/unifi-mcp/blob/main/SECURITY.md): Supported reporting and security guidance. ## Architecture - [Architecture](https://github.com/sirkirby/unifi-mcp/blob/main/docs/ARCHITECTURE.md): Component responsibilities
sno-ai/sno-station/llms.txt
runs - docs/ — setup guides for the four memory integrations, images, evidence, translations, security page - tests/apps/ — public-contract tests only ## Contributing - CONTRIBUTING.md — DCO sign-off, one change per PR, which checks
Steady3 mentions in 2 weeks
No other project uses it yet
Electricitysheep/dsh-handbook/llms-full.txt
Chinese, EN translations) covering install, profiles, plugin development, performance tuning, tools & context, MCP & subagents, security & sandbox, cache & cost engineering, ecosystem panorama. Includes same-model multi-agent benchmark (omp/dsh/opencode, 45/45), quickstart
Electricitysheep/dsh-handbook/llms.txt
Chinese, EN translations) covering install, profiles, plugin development, performance tuning, tools & context, MCP & subagents, security & sandbox, cache & cost engineering, ecosystem panorama. Includes same-model multi-agent benchmark (omp/dsh/opencode, 45/45), quickstart
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.