graph-memory

A local project-memory tool that stores code structure, agent decisions, and searchable session information in a SQLite database. It can create repeatable summaries for use in future prompts.

In plain words
What is it for?
Use it to index Python, TypeScript, Go, or Rust code, search project and session history, review past agent decisions, detect contradictions, and create token-limited context snapshots.
Why use it?
It helps coding agents avoid losing project context between sessions and highlights conflicting decisions. Repeatable summaries can also keep unchanged prompts consistent.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/divyanshailani/graph-memory/graph-memory
Any agent
npx skills add divyanshailani/graph-memory --skill graph-memory
Clone the repo
git clone --depth 1 https://github.com/divyanshailani/graph-memory

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 876 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00045 $0.00876
Opus 5 $0.00023 $0.00438
Sonnet 5 $0.00009 $0.00175
Haiku 4.5 $0.00005 $0.00088

Measured 2d ago against content hash 026225609258, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

graph-memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Graph Memory

A local SQLite knowledge graph at .agents/graph_memory.sqlite that gives AI coding agents long-term project memory. Ingests codebase AST (Python, TypeScript, Go, Rust via Tree-sitter), tracks agent decisions in an append-only ledger, detects contradictions between agents, and produces prompt-cache-stable snapshots.

Installation

pip install epistemic-graph-memory[all]

MCP Server

{"mcpServers":{"graph-memory":{"command":"graph-memory-mcp"}}}

Streamable HTTP (for OpenCode, Docker, remote agents):

graph-memory-mcp-http    # http://127.0.0.1:8765/mcp

CLI

Ingest

graph-memory ingest-code .                    # full codebase AST + call graphs
graph-memory ingest-file src/engine.py        # single file re-parse (<5ms)

Snapshots

graph-memory snapshot --max-tokens 600 --min-trust 0.7

Output is deterministic and content-fingerprinted — unchanged graph returns identical bytes so prompt caches stay warm.

Search

graph-memory search "effective_tr"            # FTS5 + identifier substring fallback
graph-memory search-sessions "trust decay"    # episodic session logs

Decision History

graph-memory query-history --agent Hermes --days 7
graph-memory contradictions                   # surfaced conflicts between agents

Lifecycle Hooks

graph-memory hook install                     # auto-configure all 9 frameworks
graph-memory hook install --framework cursor
graph-memory hook status
graph-memory hook refresh                     # re-render snapshots now

Supported: Claude Code, ZCode, Cursor, Codex, OpenCode, Antigravity, Qoder, Hermes, Claude Desktop.

Events: PostToolUse (incremental AST ingest <5ms), Stop (transcript distillation + fact extraction), SessionStart (snapshot refresh).

Import / Export

graph-memory import-md CLAUDE.md              # markdown sections → Knowledge_Nodes
graph-memory import-mem0 memories.json        # mem0 JSON → Fact_Nodes
graph-memory export-obsidian ~/vault           # Obsidian vault with [[wikilinks]]

Read the full file on GitHub · 114 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 114 lines · 45 tokens per session scan A 026225609258

Subscribe to this mod's changes

graph-memory is a skill published in the GitHub repository divyanshailani/graph-memory (17 stars, last pushed 11d ago), licensed MIT. It adds 45 tokens to every session and 876 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens