openexp
openexp is an MCP server, listed under memory & vectors. It reaches qdrant. Its repository has 59 GitHub stars and is licensed under MIT; we last read it on 2026-10-22.
Outsource your understanding. Capture every human-AI decision as a step in a trajectory; grade trajectories retroactively when outcomes land (deal closed, sprint shipped). Hooks + MCP server for Claude Code, Qdrant + FastEmbed local-first.
Install
MCP servers are packaged differently from each other -- some run via npx, some as a Docker image, some as a plain script you clone and run. openexp’s own README did not state one plainly enough for this page to quote it rather than guess, so it will not guess. The repository below states it.
What it reaches, and what it needs
What it connects to
Unverified means a mention in the server’s own description, not a citation. A wrong claim here costs nothing to correct and nothing to trust yet.
Maintenance
Outsource your understanding. Capture every human-AI decision as a step in a trajectory; grade trajectories retroactively when outcomes land (deal closed, sprint shipped). Hooks + MCP server for Claude Code, Qdrant + FastEmbed local-first.
openexp compared with similar servers
| Server | Reaches | Needs | Stars | Last update | Licence |
|---|---|---|---|---|---|
| openexp (this page) | qdrant | None listed | 59 | 2026-09-19 | MIT |
| mcp-server-qdrant | qdrant(1 shared) | QDRANT_API_KEY | 1,553 | 2026-09-04 | Apache-2.0 |
| mem0-mcp-selfhosted | google, qdrant(1 shared) | GOOGLE_API_KEY | 111 | 2026-03-13 | MIT |
| skills-mcp | qdrant, workers(1 shared) | QDRANT_API_KEY, WORKERS_AI_API_TOKEN | 10 | 2026-05-29 | Apache-2.0 |
| mcpdeck | qdrant(1 shared) | None listed | 2 | 2026-07-16 | MIT |
| imprint-memory-layer | qdrant(1 shared) | None listed | 0 | 2026-05-27 | Apache-2.0 |
Ranked by services in common with openexp, then by stars. Figures are from each repository when we last read it.
Common questions about openexp
- What does openexp do?
- Outsource your understanding. Capture every human-AI decision as a step in a trajectory; grade trajectories retroactively when outcomes land (deal closed, sprint shipped). Hooks + MCP server for Claude Code, Qdrant + FastEmbed local-first.
- How do I install openexp?
- Its README did not state an install command plainly enough for us to quote one, so we do not guess. The repository has the instructions: https://github.com/anthroos/openexp
- What does openexp connect to, and what does it need?
- It reaches qdrant.
- Which AI clients can use openexp?
- Its own description mentions Claude Code. That is a mention in its description, not a test we ran.
- Is openexp official and is it maintained?
- We found nothing naming it as a vendor’s official server. Its repository has 59 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-09-19.
- What licence does openexp use?
- The repository declares the MIT licence.
More MCP servers for memory & vectors
- mcp-server-qdrant1,553 stars
- mcp-knowledge-graph886 stars
- chroma-mcp601 stars
- caura504 stars
- MemoryMesh354 stars
- neural-memory242 stars