deciduous
llms.txt171 starsChanged 23 days agoApache-2.0View on GitHub
A decision graph for AI-assisted development. Agents and people write goals, options, decisions, actions and outcomes to a shared server (PostgreSQL behind an authenticated HTTP MCP endpoint), one workspace per repository. Deciduous 1.1.0. Every page below is Markdown. The whole set in one file: https://deciduous.dev/llms-full.txt
- Reads credentials
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- docs/llms-full.txtllms.txt
The file
We split this llms.txt 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
Every page below is Markdown.
≈ “Common” is an estimate: at least 1 in 5 of the 3,727 llms.txt 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
# Deciduous > A decision graph for AI-assisted development. Agents and people write goals, options, decisions, actions and outcomes to a shared server (PostgreSQL behind an authenticated HTTP MCP endpoint), one workspace per repository. Deciduous 1.1.0. Every page below is Markdown. The whole set in one file: https://deciduous.dev/llms-full.txt ## Get started - [One decision graph for every agent on the team](https://deciduous.dev/content/index.md): Deciduous records why the code is the way it is: what was asked, the approaches considered, the one chosen and what it beat, what was changed, and what happened. The graph lives on a server your team - [Join your team's graph server](https://deciduous.dev/content/quickstart.md): You need two things from whoever runs the server: its base URL and its token. With those, five commands connect a repository: remote login stores the token, remote setup --url points the repository at - [Run a server for your team](https://deciduous.dev/content/run-a-server.md): A deciduous server is two containers, the server and PostgreSQL, on one machine behind an HTTPS proxy. You start it once, then give each person a URL and a token. Every developer's CLI and every agent - [Connect your coding agents](https://deciduous.dev/content/clients.md): Every client connects to the same thing: /mcp over Streamable HTTP, with Authorization: Bearer . What differs is where each client keeps that registration and whether it pins a workspace. The one thin - [For agents: setting up and using deciduous](https://deciduous.dev/content/for-agents.md): This page is written to you, the coding agent that was told "set up deciduous here" or "use deciduous". The graph lives on a server the user's team runs; your job is to connect this repository to that ## Work in the graph - [Record the work as goal, options, decision, action, outcome](https://deciduous.dev/content/workflow.md): A useful graph answers two questions for whoever comes next: what was asked for, and what has already been tried. Write each node at the moment it happens, on the server everyone shares: an agent thro - [Many agents, one workspace](https://deciduous.dev/content/teams.md): Every agent and every person on a project writes to the same workspace on the same server, each on its own git branch. Nothing locks: two sessions writing one branch both succeed and their nodes inter - [Agents message each other on the board](https://deciduous.dev/content/board.md): Two agents working at the same time need to ask each other things: is this response shape stable, did you move those fixtures, I am about to change this interface. The message board is where they do i - [Pick up where the last session stopped](https://deciduous.dev/content/recovery.md): A new session starts with nothing but the repository, and the graph on the server holds everything the last one decided. Recovery is reading that graph before writing anything: the goal still open, th - [Attach the evidence, or derive the graph from it](https://deciduous.dev/content/evidence.md): A node is only as good as what backs it. Deciduous has two ways to put evidence next to a claim: attach a file to a node with deciduous doc attach, which in a project with a [remote] uploads the bytes - [Keep the approaches that were abandoned](https://deciduous.dev/content/history.md): When an approach turns out wrong, the useful record is not the corrected decision alone but the chain that replaced it: the old decision, the observation that killed it, a revisit, and the new decisio ## Operate - [Backups, upgrades, tokens](https://deciduous.dev/content/operating.md): There are two things to look after: the PostgreSQL database and the .env file next to it. The server itself holds no state, so if you rebuild it from the same .env against the same database, the graph - [Without a shared server](https://deciduous.dev/content/local.md): There are two fallbacks for when nobody runs a server you can join. deciduous remote setup --local runs the same server on your own machine as a background service, so the CLI and your agents work exa - [Troubleshooting](https://deciduous.dev/content/troubleshooting.md): Most problems are one of four things: the CLI and the agent are talking to different servers, the token in use belongs to a different server, the workspace name collides with another repository, or th ## Reference - [Graph concepts](https://deciduous.dev/content/concepts.md): A deciduous graph is typed nodes joined by typed, directed edges, kept per workspace (one per repository) on a shared server. Seven node types, seven edge types, six statuses, and a confidence from 0 - [CLI reference](https://deciduous.dev/content/reference.md): The deciduous commands people actually use, grouped by what you are trying to do, with flags as deciduous --help prints them in 1.1.0. In a project connected to a server (one whose .deciduous/config.t - [MCP tools](https://deciduous.dev/content/mcp.md): There are two MCP servers with different tool sets, and an agent gets whichever one its client is configured for. - [Architecture and trust](https://deciduous.dev/content/architecture.md): The graph lives in PostgreSQL behind one server process. Agents reach that server over HTTPS MCP; the CLI reaches the same server, over the same HTTPS and token, through ordinary JSON endpoints (/ops, - [Develop deciduous](https://deciduous.dev/content/developer.md): The repository holds three things that are built and tested separately: the Rust CLI at the root (cargo), the graph server in deciduous_mcp/ (Elixir, mix), and two web builds, the graph viewer in web/
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.

