Skip to content
RobothecaBeta
Log in

robotmem

  • Software
  • Humanoids and robot learning
  • Library

A Python library and MCP server that lets robots store and retrieve their episode experiences, such as parameters, trajectories and outcomes, to guide later decisions.

Source on GitHub: github.com/robotmem/robotmem (opens in a new tab). Facts read at commit c3e2ec2 (opens in a new tab).

Licenses

Code
Apache-2.0 (opens in a new tab)

Read by Robotheca from LICENSE (opens in a new tab) (Apache-2.0) at commit c3e2ec2 (opens in a new tab), on 22 Oct 2026.

Commercial use
Yes

What it does

  • Records physical experiences like parameters, strategies and lessons via learn, and stores perception or trajectory data via save_perception.
  • Retrieves experiences with hybrid BM25 and vector search, filtered by structured context and sorted by spatial nearest-neighbor.
  • Stores everything in a local single-file SQLite database with FTS5 and vec0 extensions.
  • End_session merges similar memories by Jaccard similarity and returns relevant memories for the next episode.
  • Offers seven APIs including forget and update for correcting memories, and can run as an MCP server or be imported directly.

Written by Robotheca from the project's README (opens in a new tab) at commit c3e2ec2.

Getting started

Difficulty
Intermediate
Hardware it needs, as the project states it
CPU-only, no GPU required.

Maintenance

Status
Maintained: a commit in the last 12 months
Newest commit
24 Mar 2026 on main
Latest release
v0.1.1 — SDK + ROS 2 Compatibility + rsl_rl Adapter (12 Mar 2026)

Checked on GitHub on 22 Oct 2026.

Links

Robots that can run it

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.