Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.
Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.
Claude Code memory that learns from corrections. The only learning loop that measures whether your agent actually stops repeating a mistake.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
claude mcp add agent-recall --env OPENAI_API_KEY=your-value -- npx -y agent-recall-mcp| Variable | Description | Required |
|---|---|---|
| OPENAI_API_KEY | Credential the server authenticates with. | Yes |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Long-term memory for agentic tasks. It tells you when it doesn't know.
Company wiki for AI: answers with citations, decisions, records and the team's board.
Universal AI Agent Discovery - search 59,000+ agents across MCP, NANDA, A2A, OpenRouter
Retrieves package documentation from multiple language ecosystems for use with LLMs.