robotmem

robotmem is a persistent memory system for robotic/agent experiences. It records episodic robot experience (parameters/strategies/trajectories/outcomes), stores perception data, and retrieves relevant past memories using hybrid search (BM25 + vector) with structured JSON filtering and optional spatial nearest-neighbor sorting. It can also run as an MCP server (7 tools) or be used directly via Python imports, with an embedded local SQLite database.

Evaluated Mar 30, 2026 (0d ago)
Homepage ↗ Repo ↗ Ai Ml ai-agents robotics episodic-memory experience-replay hybrid-search semantic-search spatial-retrieval sqlite python mcp-server offline-first
⚙ Agent Friendliness
54
/ 100
Can an agent use this?
🔒 Security
27
/ 100
Is it safe for agents?
⚡ Reliability
22
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
55
Documentation
65
Error Messages
0
Auth Simplicity
95
Rate Limits
10

🔒 Security

TLS Enforcement
10
Auth Strength
20
Scope Granularity
0
Dep. Hygiene
55
Secret Handling
60

Appears to be local/offline-first using embedded SQLite, which reduces network attack surface, but no auth model, TLS requirements, or secret-handling/logging guarantees are documented. It includes an MCP server and optional web management UI (flask), but security configuration (auth, CSRF, TLS, CORS, rate limiting) is not documented in the provided materials.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
30
Error Recovery
25
AF Security Reliability

Best When

You have robotics/agent experiments where you can run a local persistent SQLite-backed memory store and want structured + spatially informed retrieval to guide future decisions.

Avoid When

You need a hosted service with enterprise-grade security, centralized access control, and documented SLAs, or you cannot store data locally.

Use Cases

  • Improving robot policies via experience replay (record → recall across episodes)
  • Retrieving only relevant prior episodes using structured constraints (e.g., task success, parameter thresholds)
  • Spatial/nearest-neighbor retrieval for scenarios with similar physical positions
  • Offline-first local long-term memory for robotics experiments (CPU-only, SQLite-backed)
  • Agent workflows that benefit from hybrid retrieval (text + embeddings) fused with reranking

Not For

  • Production multi-tenant SaaS scenarios requiring managed hosting, auth, and auditability
  • Use cases that require network-based low-latency shared memory at scale across many users
  • Environments that require strong enterprise compliance controls (SOC2/HIPAA/etc.) out of the box

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication mechanisms are described in the provided README/manifest. The system appears to be local/offline-first (embedded SQLite, CPU-only) and thus likely used without external auth unless the MCP/web UI adds it (not documented here).

Pricing

Free tier: No
Requires CC: No

Apache-2.0 library; no pricing details provided.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • No documented rate limiting behavior (local usage likely, but MCP/UI could differ).
  • Structured filtering expects specific JSON field paths and operators (e.g., $lt); incorrect schema/paths may lead to empty/incorrect recall without clear guidance.
  • Spatial sorting depends on consistent coordinate field naming and the expected 'spatial.*' structure; mismatches may reduce retrieval quality.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for robotmem.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6533
Packages Evaluated
19870
Need Evaluation
586
Need Re-evaluation
Community Powered