MegaMemory alternatives
Curated alternatives to MegaMemory — and why you'd switch.
codegraph-mcp
No-train, on-prem code knowledge graph served to AI agents over MCP — symbols, call edges, cross-language links and blast-radius queries, with a hash-chained audit log of every read.
Why switchTwo ways to hand an agent a graph of the repo: codegraph-mcp derives symbols, call edges and blast radius mechanically from source, MegaMemory stores the concepts and decisions an agent wrote down. Mechanical facts vs. curated intent.
Full comparison →codebase-memory-mcp
Code intelligence MCP in pure C: tree-sitter knowledge graph over 158 languages, average repo indexed in milliseconds, sub-ms queries, 10x fewer tokens. Single static binary, zero deps.
Why switchcodebase-memory-mcp indexes structure with tree-sitter in milliseconds and answers 'what calls this'; MegaMemory holds LLM-authored concepts with embeddings and answers 'why is it like this'. Choose by the question you keep re-asking.
Full comparison →agentmemory
Persistent memory for coding agents on the iii engine: MCP server with 53 tools, 12 auto-capture hooks, hybrid search + knowledge graph, zero external DBs. Claims 95% R@5 and 92% token cuts.
Why switchBoth are MCP memory servers for coding agents combining a graph with semantic search; agentmemory auto-captures through hooks, MegaMemory expects the agent to curate concepts deliberately — less noise, more discipline required.
Full comparison →