RobotMem

robotmem — Let Robots Learn from Experience

Your robot ran 1000 experiments, starting from scratch every time. robotmem stores episode experiences — parameters, trajectories, outcomes — and retrieves the most relevant ones to guide future decisions.

FetchPush experiment: +25% success rate improvement (42% → 67%), CPU-only, reproducible in 5 minutes.

from robotmem import learn, recall, save_perception, start_session, end_session # Start an episode session = start_session(context='{"robot_id": "arm-01", "task": "push"}') # Record experience learn( insight="grip_force=12.5N yields highest grasp success rate", context='{"params": {"grip_force": {"value": 12.5, "unit": "N"}}, "task": {"success": true}}' ) # Retrieve experiences (structured filtering + spatial nearest-neighbor) memories = recall( query="grip force parameters", context_filter='{"task.success": true}', spatial_sort='{"field": "spatial.position", "target": [1.3, 0.7, 0.42]}' ) # Store perception data save_perception( description="Grasp trajectory: 30 steps, success", perception_type="procedural", data='{"sampled_actions": [[0.1, -0.3, 0.05, 0.8], ...]}' ) # End episode (auto-consolidation + proactive recall) end_session(session_id=session["session_id"])

Not just vector search — robotmem understands the structure of robot experiences:

# Retrieve only successful experiences recall(query="push to target", context_filter='{"task.success": true}') # Find spatially nearest scenarios recall(query="grasp object", spatial_sort='{"field": "spatial.object_position", "target": [1.3, 0.7, 0.42]}') # Combine: success + distance < 0.05m recall( query="push", context_filter='{"task.success": true, "params.final_distance.value": {"$lt": 0.05}}' )

{ "params": {"grip_force": {"value": 12.5, "unit": "N", "type": "scalar"}}, "spatial": {"object_position": [1.3, 0.7, 0.42], "target_position": [1.25, 0.6, 0.42]}, "robot": {"id": "fetch-001", "type": "Fetch", "dof": 7}, "task": {"name": "push_to_target", "success": true, "steps": 38} }

Each recalled memory automatically extractsparams/spatial/robot/taskas top-level fields.

- Consolidation: Merges similar memories with Jaccard similarity > 0.50 (protects constraint / postmortem / high-confidence entries)
- Proactive Recall: Returns historically relevant memories for the next episode

cd examples/fetch_push pip install gymnasium-robotics PYTHONPATH=../../src python demo.py # 90 episodes, ~2 min

Three-phase experiment: baseline → memory writing → memory utilization. Expected Phase C success rate 10-20% higher than Phase A.

SQLite + FTS5 + vec0 ├── BM25 full-text search (jieba CJK tokenizer) ├── Vector search (FastEmbed ONNX, CPU-only) ├── RRF fusion ranking ├── Structured filtering (context_filter) └── Spatial nearest-neighbor sorting (spatial_sort)

- CPU-only, no GPU required
- Single-file database~/.robotmem/memory.db
- MCP Server (7 tools) or direct Python import
- Web management UI:robotmem web

Chia Health MCP Server — Patient workflow integration for a licensed US telehealth platform. Browse GLP-1 medications (semaglutide, tirzepatide), peptide therapies (sermorelin, NAD+, glutathione), and longevity treatments. Check eligibility, complete intake, sign consents, and manage treatment plans. 30 tools, HIPAA-compliant. All prescriptions evaluated by licensed US healthcare providers and delivered from FDA-regulated pharmacies across 50 states + DC.

Broker + MCP server for last-bidder-wins games on Solana — agents register, auto-fund a Privy wallet, and bid via streamable HTTP

AI-powered no-code app builder with 17 MCP tools — create projects, generate pages from natural language, AI text/image generation (GPT, Claude, Gemini, 14+ models), page CRUD, workflow execution, publish & version control. SSE transport, API key auth.

An mcp server for your food ordering needs.

Agent-to-Agent handoff certification for multi-agent systems — validates context preservation, verifies agent capabilities before handoff, logs transfer chains, and ensures no data loss in agent orchestration.

Unified MCP & skill management gateway with progressive disclosure. Manages multiple MCP servers as Agent Apps, loading tool schemas on demand for 99% context token savings. Shared across Claude Code, Codex, OpenCode and more.

A collection of Model Context Protocol (MCP) servers for various tasks and integrations, supporting both Python and Node.js environments.

Open-souSecurely feeds real security refreshed rules into Cursor, Claude Code, and Windsurf — zero config, no API key.

Health intelligence MCP — access biomarkers, biological age, and personalized longevity action plans from your Aniva profile.

Real-time stock heatmaps and investment tools delivered as interactive React components.