Agent Memory
Provides a shared, durable memory store backed by SQLite that multiple AI coding agents can read and write to. Agents contribute facts and context to a common local database, enabling persistent memory that survives across sessions and tools. Supports both lexical retrieval and optional semantic search via Ollama embeddings, with built-in session importers for Codex, Claude Code, and ChatGPT export archives. Includes client-adaptive response shaping, canonical preference resolution with last-write-wins semantics, and idempotent upsert operations with redaction heuristics.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/mikeylong/agent-memory-mcp
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Agent Memory from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.