erishforGllms.txtgit-parsec
erishforG/git-parsec/docs/llms.txt
itself — you still use `git add`, `git commit` inside each worktree - Not a code review tool — it opens PRs and monitors them; review happens on the forge
llms.txt examples
How real projects summarise themselves for language models.
Best matches · from page 19Worked for most · soon
erishforGllms.txt
mohamed-ashraf-elsaedllms.txtclaude-agent-sdk-laravel
mohamed-ashraf-elsaed/claude-agent-sdk-laravel/llms-full.txt
developers to build AI-powered agents directly in PHP/Laravel. The SDK communicates with Claude Code via subprocess, parses streaming JSON output, and provides a fluent PHP API. ## Installation composer require
shalintripathillms.txtsaas-marketing-agents
shalintripathi/saas-marketing-agents/llms.txt
they also work by copying them into any AI coding tool (Cursor, Claude Code, Copilot, Aider, Windsurf). ## Start here - [README](README.md): what the project is, quick start, and the full
skein-jsllms.txtskein-js
skein-js/skein-js/llms-full.txt
ways in**, both mounting the same Agent Protocol server. **Already have a compiled graph in code (no `langgraph.json`, never used the LangGraph Platform)?** Bring it directly — pass a graph
sno-aillms.txtsno-station
sno-ai/sno-station/llms.txt
Open-source software that turns the coding agents a developer already pays for (Claude Code, > Codex, OpenClaw) into one squad on their own machine (Sno Station is the agents' workstation
spec-ops-methodllms.txtspec-ops
spec-ops-method/spec-ops/docs/llms.txt
Specification Generation** - Use AI agents to create initial specifications from legacy code 3. **Specification Verification** - Domain experts review and validate specifications 4. **Modern Implementation** - Generate new code from verified specifications
thevibeworksllms.txtclaude-reads-hn
thevibeworks/claude-reads-hn/llms.txt
# Claude Reads HN > AI-curated HN digests every 5 hours. Check story IDs before
verivus-ossllms.txtllm-cli-gateway / site
verivus-oss/llm-cli-gateway/site/llms.txt
configured API providers through one local control plane. It is best for cross-model code review, durable long-running jobs, provider-native session continuity, approval gating, and remote HTTP
webrenewllms.txtunicon
webrenew/unicon/LLMs.txt
icons across libraries - Suggesting alternatives when switching libraries - Confidence scoring for match quality - Manual review flagging for uncertain matches ### Starter Packs Curated icon collections for common use cases: - Dashboard icons
wonsukchoillms.txtdomain-experts
wonsukchoi/domain-experts/docs/llms.txt
space, evaluating a wall or floor assembly's STC/IIC rating against a code or… - [Adhesive Bonding Machine Operator](https://domainexperts.dev/roles/adhesive-bonding-machine-operator/): distinguishing an open-time violation from a pot-life
Alessandro-Pangllms.txtharnessmith
Alessandro-Pang/harnessmith/llms.txt
user's request. Accepted values are `codex`, `cursor`, `claude`, `claude-code`, `opencode`, `kimi`, `kimi-code`, `deepseek`, `dsh`, `deepseek-harness`, `pi`, `pi-agent`, and `all`. Never infer `all` from an ambiguous
ASGComputellms.txtasgcard-public
ASGCompute/asgcard-public/llms-full.txt
approval_required` + `approvalUrl` 2. Owner opens the approval page at stripe.asgcard.dev/approve 3. Owner reviews and approves → Stripe Elements form with real-time pricing 4. Owner pays via Stripe → card/Apple
jimy-rllms.txtagent-workspace-architecture
jimy-r/agent-workspace-architecture/docs/llms-full.txt
beats the obvious alternative, and what it costs. The file conventions are Claude Code's; the patterns travel to any agent runtime. Read this when you want the *why*. [META_ARCHITECTURE.md
jimy-rllms.txtagent-workspace-architecture
jimy-r/agent-workspace-architecture/docs/llms.txt
building agent workspaces: the roles, routines, hooks, memory, and task coordination that turn a coding agent into a system you can hand work to. One person's working setup, published
jvoganllms.txtsymphony-linear-starter
jvogan/symphony-linear-starter/llms.txt
self-improving runbook loop. ## Key concepts - **Orchestrator**: Your Codex or Claude Code agent. Plans issues, dispatches workers, reviews output, promotes learnings. - **Symphony**: OpenAI's open-source runtime for dispatching isolated
lacymorrowllms.txtpaperclip-hub
lacymorrow/paperclip-hub/public/llms-full.txt
anneal-memory/paperclip-plugin ## Notification Sound Plays a notification sound when issues change to in_review, blocked, or done. - URL: https://cliphub.fyi/plugins/paperclip-plugin-notification-sound - npm: paperclip-plugin-notification-sound (v1.0.3) - Category: tools
log-bellllms.txtavakill
log-bell/avakill/llms.txt
command": "rm -rf /"}}' | avakill evaluate --policy avakill.yaml # deny: Matched rule 'block-dangerous-shells' ``` Exit codes: `0` = allowed, `2` = denied, `1` = error. --- ## Policy Format Policies are YAML files. Rules are evaluated
log-bellllms.txtavakill / site
log-bell/avakill/site/llms.txt
command": "rm -rf /"}}' | avakill evaluate --policy avakill.yaml # deny: Matched rule 'block-dangerous-shells' ``` Exit codes: `0` = allowed, `2` = denied, `1` = error. --- ## Policy Format Policies are YAML files. Rules are evaluated
Mnemosyne-OSllms.txtMnemosyne-Neural-OS
Mnemosyne-OS/Mnemosyne-Neural-OS/llms.txt
Mnemosyne OS — build reference for LLMs & coding agents > Mnemosyne OS is a sovereign, local-first memory operating system — the > relationship layer for AI. This file is the *developer* entry point
remembra-aillms.txtremembra / landing
remembra-ai/remembra/landing/llms-full.txt
self-hosted server, the user adds `--url` and their server's URL. Exit code 3 means it showed the changes and wrote nothing. ### 6. Show the hook changes ```bash remembra
About llms.txt
What is llms.txt?
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.
What's llms-full.txt?
The same idea with the content included, so an agent can read the documentation in one request.
Who reads it?
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
How do I write one?
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.