OmniMem
PulseGate's liveness check found it on 19 Sep 2026; it is registered on GitHub and has been in the index since 19 Sep 2026. How this is checked
OmniMem is an open-source, MIT-licensed MCP server that gives coding agents persistent semantic memory across sessions, projects, and machines. It supports memory lifecycle management, abandoned-approach warnings, experience scoring, contradiction detection, and RSS knowledge ingestion on self-hosted hardware.
Inferred · not functionally tested
Overview
6 featuresPurpose: Preventing AI coding agents from losing project context, past decisions, and failed approaches between sessions.
Inferred · not functionally tested
Audience: developers building or using AI coding agents
Inferred · not functionally tested
Functions: rag, agents
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: MIT · platforms: API, CLI, WEB · deployment: browser, cli, api_only, self_hosted
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: omnimem.org · github.com. These links do not verify the individual claims.
OmniMem is a Memory & skills project. Inferred · not functionally tested: It focuses on preventing AI coding agents from losing project context, past decisions, and failed approaches between sessions. Inferred · not functionally tested: It is built as an open-source project for developers building or using AI coding agents. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: It runs on the web, the command line, and API, and it can be self-hosted.
Richard Harvey builds and maintains OmniMem, and it first shipped in 2026. Development happens publicly on GitHub with 59 stars and 128 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include persistent memory, semantic retrieval, and memory lifecycle. Inferred · not functionally tested: Catalogued interfaces include an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Persistent memory
- Semantic retrieval
- Memory lifecycle
- Abandoned-approach warnings
- Experience scoring
- Contradiction detection
Topics: Inferred · not functionally tested
Built with & integrations
- Claude Code
- commit 83987893256f · since Jul 2026
- anthropic
- bclaude in the HTML
- local_oss
- bollama in the HTML
- Cloudflare
- cf-ray header · cf-cache-status header
Trust & compliance
Indexing history
2What PulseGate has recorded for this listing
Frequently asked questions about OmniMem
- What is OmniMem?
- Inferred · not functionally tested: OmniMem focuses on preventing AI coding agents from losing project context, past decisions, and failed approaches between sessions. It is catalogued under Memory & skills on PulseGate.
- Who is OmniMem for?
- Inferred · not functionally tested: OmniMem is an open-source project built for developers building or using AI coding agents.
- Does OmniMem have a free plan?
- Basis unknown · not verified: Yes — OmniMem is open source under the MIT license and free to use.
- What platforms does OmniMem run on?
- Basis unknown · not verified: OmniMem runs on the web, the command line, and API. It can also be self-hosted.
- Is OmniMem still maintained?
- PulseGate's liveness check found it on 19 Sep 2026. Its GitHub repository shows 128 commits in the last 90 days.
- What are alternatives to OmniMem?
- Similar projects tracked by PulseGate include Agent Memory MCP, AutoMem, and memo.Agent Memory MCPAutoMemmemo
- Who makes OmniMem?
- OmniMem is developed by Richard Harvey.
- How long has OmniMem been around?
- OmniMem first shipped in 2026.
Similar projects
Closest matches by what these projects do