rag-remember
Skill2 starsChanged 7 months agoMITView on GitHub
Store a fact, decision, or observation into the personal LightRAG knowledge graph immediately
- Reads credentials
- Sends data out
In this repository6 other files it gives its agents.
- rag-project-querySkill
- rag-project-rememberSkill
- rag-project-syncSkill
- rag-querySkill
- rag-setup-projectSkill
- rag-syncSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 68
Do NOT dump the raw API response
- Distinctive: line 69
If the insert fails, tell the user and suggest trying again
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
RAG Remember — Store to Personal Knowledge Graph
Store a specific fact, decision, or observation into your personal LightRAG knowledge graph. Use mid-session when something worth remembering comes up.
Formatting rules
Format each entry as:
[TYPE] Title — YYYY-MM-DD
What: Brief description of the fact or decision
Why: The reasoning or context behind it
Files: Relevant file paths (if applicable)Entry types
| Type | Use for |
DECISION | Architecture choices, tool selections, approach decisions |
FEEDBACK | User corrections, preferences, "do this / don't do that" |
CONFIG | Server settings, env vars, ports, credentials (NO actual secrets) |
PROJECT | Project status, goals, deadlines, stakeholders |
PERSON | People, roles, contact preferences, working styles |
REFERENCE | URLs, docs, external resources, where to find things |
INSIGHT | Debugging lessons, performance findings, non-obvious learnings |
How to store
node -e "
const BASE = process.env.LIGHTRAG_SERVER_URL || 'http://YOUR_LIGHTRAG_HOST:YOUR_PERSONAL_PORT';
(async () => {
const auth = await fetch(BASE + '/auth-status').then(r => r.json());
const token = auth.access_token;
const res = await fetch(BASE + '/documents/text', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'Authorization': 'Bearer ' + token
},
body: JSON.stringify({
file_source: '[TYPE] Title — YYYY-MM-DD',
text: 'Full content here with What/Why/Files structure'
})
});
const data = await res.json();
console.log('Status:', res.status);
})();
"After inserting
- Confirm to the user: "Stored: [TYPE] Title"
- Do NOT dump the raw API response
- If the insert fails, tell the user and suggest trying again
What NOT to store
- Ephemeral task details — current conversation context, in-progress work steps
- Code from the codebase — it's already in the repo; store the decision, not the code
- Duplicates — query first if unsure whether something is already stored
- Credentials or secrets — never store API keys, passwords, tokens
- Git history — use
git log/git blameinstead
Infrastructure
- Server:
YOUR_LIGHTRAG_HOST:YOUR_PERSONAL_PORT - Auth: Bearer token from
/auth-status(guest/disabled mode) - Env var:
LIGHTRAG_SERVER_URL
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.

