About Agent Memory Engine
Agent Memory Engine is an MCP server in the Security category: a long-term memory engine for coding agents: two-stage retrieval + gating, hybrid (vector + BM25) search, optional cross-encoder rerank, Ebbinghaus decay, and cross-session collaboration. SQLite-backed, drop-in MCP server.
The repository has 5 stars and 0 forks.
Install
git clone https://github.com/uudam42/agent-memory-engineThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (7)
inspect_knowledgeInspect a KnowledgeChunk or source file range (redacted)
Parameters not published.
inspect_memoryDrill into a MemoryNode, its children, and evidence
Parameters not published.
memory_statusProject health, retrieval mode, index counts, revisions
Parameters not published.
reflect_and_writeReport validated work to the reflection pipeline
Parameters not published.
refresh_project_knowledgeTrigger incremental rescan; also builds Phase 10 proposition/paragraph/summary layers
Parameters not published.
retrieve_agent_contextRetrieve memory + knowledge before a coding task. Phase 10: pass `task_intent`, `preferred_layers`, `proposition_types` to guide granularity routing.
Parameters not published.
seed_project_context**Call once on new projects.** Write initial constraints, decisions, project description, and conventions directly as active memory nodes. Auto-extracts from README.md when fields are omitted. Eliminates cold-start problem.
Parameters not published.
Ask AI
Ask AI about Agent Memory Engine
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.