#567 · Primary category: AI Coding Assistants

MegaMemory

agentic-coding ai ai-agents claude-code code-context coding-agent embeddings knowledge-graph llm mcp mcp-server opencode persistent-memory sqlite typescript

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