#567 · Primary category: AI Coding Assistants
MegaMemory
Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer.
Project last updated:05/03/26
GitHub Stars
514
Forks
47
Contributors
2
License
MIT
Why we included this project
Coding agents lose their hard-won context when a session closes, and this MCP server gives them somewhere to keep it. Whatever an agent learns about a project gets saved as a persistent, per-project knowledge graph in SQLite, which the agent can then query in plain language before starting the next task. The interesting part is that the LLM does the indexing itself: no AST parsing or static analysis, so concepts are recorded in the agent's own words and the graph holds intent rather than bare code symbols. A single install command wires it into editors like Claude Code and opencode, and it ships a browser-based explorer for visualizing the graph plus merge commands to sync knowledge across divergent branches.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.