agentmemory
PulseGate's liveness check found it on 8 Oct 2026; it is registered on GitHub and has been in the index since 28 Aug 2026. How this is checked
agentmemory is a local memory runtime for AI coding agents that captures session activity, consolidates observations, and retrieves relevant context later. It combines BM25, vector, and knowledge-graph retrieval, exposes MCP tools and REST endpoints, and runs without external databases.
Inferred · not functionally tested
Overview
6 featuresPurpose: Preserving and retrieving coding-agent context across sessions without external databases.
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: unknown · license: Apache-2.0 · platforms: CLI, WEB · deployment: browser, cli, api_only, self_hosted
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: agent-memory.dev · github.com. These links do not verify the individual claims.
In the Memory & skills space, agentmemory takes a focused approach. Inferred · not functionally tested: It focuses on preserving and retrieving coding-agent context across sessions without external databases. Inferred · not functionally tested: It is built as an open-source project for developers building or using AI coding agents. Basis unknown · not verified: It ships for the web, the command line, and API, and it can be self-hosted.
agentmemory first shipped in 2026. Development happens publicly on GitHub with 27.6k stars and 59 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include session capture, hybrid retrieval, and vector search. Inferred · not functionally tested: Catalogued interfaces include an MCP server and a public API.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Session capture
- Hybrid retrieval
- Vector search
- Knowledge graph
- Memory consolidation
- MCP tools
Topics: Inferred · not functionally tested
Built with & integrations
- Next.js
- x-nextjs-prerender header · /_next/static/ in the HTML · __next_f in the HTML
- Vercel
- x-vercel-id header · x-vercel-cache header
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
Frequently asked questions about agentmemory
- What is agentmemory?
- Inferred · not functionally tested: Agentmemory focuses on preserving and retrieving coding-agent context across sessions without external databases. It is catalogued under Memory & skills on PulseGate.
- Who should use agentmemory?
- Inferred · not functionally tested: agentmemory is an open-source project built for developers building or using AI coding agents.
- What platforms does agentmemory run on?
- Basis unknown · not verified: agentmemory runs on the web, the command line, and API. It can also be self-hosted.
- Is agentmemory still active?
- PulseGate's liveness check found it on 8 Oct 2026. Its GitHub repository shows 59 commits in the last 90 days.
- What projects are similar to agentmemory?
- Similar projects tracked by PulseGate include Agent Memory MCP, AgentMem, and agent-memory-kit-cli.Agent Memory MCPAgentMemagent-memory-kit-cli
- How long has agentmemory been around?
- agentmemory first shipped in 2026.
- Is agentmemory open source?
- Basis unknown · not verified: agentmemory has a public GitHub repository.
- Does agentmemory have an API or integrations?
- Inferred · not functionally tested: Yes — agentmemory exposes an MCP server and a public API.
Similar projects
Closest matches by what these projects do