MCP Tools DirectoryAbout this integration
A self-improving, verifiable memory layer for AI coding agents.
- Transport
- stdio
- Authentication
- api-key
- Initial setup
- credentials
- Runtime
- unattended
- Evidence
- documented
- Version
- 2.7.1
- Package
- cogmem
- Last compatibility test
- Not independently tested
Connect your agent
cogmemPublisher README and pyproject manifest reviewed from hash-pinned captures. Qualification covers the documented stdio MCP configuration and credential boundary; the package, hooks, daemon, models, and external API were not executed or independently security-audited.
Capabilities: Memory recall, Memory notes, Memory verification, Project state, Progress tracking
Connected profiles
Additional details
io.github.writerslogic/cogmem
Source ↗ · Checked 2026-09-172.7.1
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17pypi
Source ↗ · Checked 2026-09-17cogmem
Source ↗ · Checked 2026-09-202.7.1
Source ↗ · Checked 2026-09-20The publisher documents background Claude Code hooks and an optional managed warm recall daemon in addition to the stdio MCP process. None of these components were executed.
Source ↗ · Checked 2026-09-20Local recall is documented as on-device, while the learning pipeline explicitly requires ANTHROPIC_API_KEY and sends relevant session transcript data to the Anthropic API; API-key credentials are therefore required for that documented learning capability.
Source ↗ · Checked 2026-09-20The publisher's MCP client configuration launches the local cogmem executable with the mcp argument over stdio.
Source ↗ · Checked 2026-09-20Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-20