- Developers using coding agents across long-running repositories
- Teams comparing persistent memory approaches for agent workflows
- Users who want a self-hosted memory layer instead of only chat history
Memory Systems
AgentMemory
Persistent memory for AI coding agents, with benchmarks and local-first workflows.
22K Stars
Apache-2.0 License
1.8K Forks
Open source
About
AgentMemory overview
AgentMemory is an open-source persistent memory layer for AI coding agents. It focuses on helping tools like Claude Code, Codex, Cursor, and related coding agents remember project context, decisions, and reusable knowledge across sessions.
Coding-agent focus
AgentMemory is framed around coding assistants rather than generic chatbot memory.
Repository conventions, architecture decisions, and implementation notes need a different memory model than casual chat.Persistent context
The project is designed to carry knowledge between agent sessions.
Persistent context reduces repeated onboarding and makes long projects less fragile.Benchmark-oriented positioning
The project emphasizes real-world memory benchmarks for coding agents.
Memory products are easy to overclaim; benchmarks help teams inspect actual workflow impact. Use cases
When to use AgentMemory
Repository memory
Store coding conventions, known pitfalls, and design decisions for future agent sessions.
Team continuity
Share durable agent context across multiple developers working in the same codebase.
Memory evaluation
Compare how much persistent memory improves coding-agent task completion.
Compare
How it compares
When to choose AgentMemory
Compare it with nearby memory systems by looking at hosting model, integration surface, license, and whether the official docs show the workflow you need.
FAQ
Questions
Is AgentMemory open source?
Yes. The repository is listed under the Apache-2.0 license.
What is AgentMemory best for?
It is best for teams using coding agents on repositories where project context changes slowly and matters across sessions.
Tags
Capabilities
Decision brief
JSON
Should you use AgentMemory?
- Teams that only need vector search for documents
- Users who do not want agents retaining project context between sessions
- Verified 2026-06-09
- License: Apache-2.0
- Repo: rohitg00/agentmemory
- Open-source signal
Deployment
cloud
Permission surface
shell/files, memory
Decision signals
No extra signals recorded
Agent packet
Structured decision data for AgentMemory
This packet is the compact machine-readable view agents should use before following source links or taking action.
Capabilities
memory
Constraints
open source
Deployment
cloud
Permission surface
shell/files, memory
Recommended workflows
Coding agent workflow, Local or private AI stack, Memory or RAG workflow
Overview
What AgentMemory does
What it is
It gives coding agents a place to store project knowledge that should survive beyond a single chat or task.
Why it matters
Agent memory is becoming a core layer in agent stacks because the agent needs context about a repo before it can make safe changes.
How to evaluate it
Start with one repository, store a small set of durable facts, and compare future agent sessions with and without the memory layer.
Facts
Known metadata and operating surface
These fields are separated from editorial interpretation so agents can reason over facts and missing checks.
Resource type memory system
Category Memory Systems
Maturity active
Difficulty Unknown
License Apache-2.0
Pricing open source
Verified 2026-06-09
Source confidence high
Risk level elevated
Fit matrix
Where AgentMemory fits in an agent stack
strong
Coding agent workflow
AgentMemory has multiple signals for coding agent workflow, including matching tags, capabilities, category, or positioning.
- Run a small repository change and inspect the diff, tests, and rollback path.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
strong
Local or private AI stack
AgentMemory has multiple signals for local or private ai stack, including matching tags, capabilities, category, or positioning.
- Verify hardware requirements, data path, storage, and whether all calls stay in your environment.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
strong
Memory or RAG workflow
AgentMemory has multiple signals for memory or rag workflow, including matching tags, capabilities, category, or positioning.
- Create, update, retrieve, correct, and delete memory or retrieval objects with real data.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial
Evaluation and observability
AgentMemory has at least one signal for evaluation and observability, but should be checked against a real task before adoption.
- Add one repeatable test case and confirm results can run again in review or CI.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
partial
Reusable skill workflow
AgentMemory has at least one signal for reusable skill workflow, but should be checked against a real task before adoption.
- Run one skill end to end and check whether it produces evidence or structured output.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
weak
Browser automation
AgentMemory is not primarily positioned for browser automation in the current metadata.
- Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.
- Confirm official docs, current maintenance, license, and runtime constraints before production use.
Inputs and outputs
What an agent should inspect
Likely inputs
- Repositories, files, issues, terminal output, and test results
- Documents, user facts, entities, context, or retrieval queries
- Official setup instructions and a small real workflow
Likely outputs
- Diffs, commits, explanations, test results, or review notes
- Retrieved context, memory updates, graph relations, or citations
- A decision on whether this resource fits the target workflow
Evidence
Sources, claims, and missing checks
Claims are marked separately from source links so future crawlers and reviewers can update them without rewriting the page.
GitHub github
Repository source for code, license, issues, releases, and implementation details.
Homepage homepageOfficial or project-controlled source for this resource profile.
AgentMemory is listed as open source.
License metadata: Apache-2.0AgentMemory has a recorded GitHub repository: rohitg00/agentmemory.
Resource facts and GitHub source link.AgentMemory supports these recorded deployment modes: cloud.
OpenAgent decision signal metadata.AgentMemory is tagged with memory capabilities.
OpenAgent capability taxonomy.- Dedicated docs link is missing.
- Repository freshness has not been recorded.
Next action
How to start evaluating AgentMemory
Inspect repository
Check license, recent activity, issues, examples, and security-sensitive code paths.
Open sourceOpen Homepage
Start from the official source before adopting third-party instructions.
Open source Compare
Alternatives and nearby resources
Use related resources to compare category fit, license, deployment model, and first-workflow behavior.
FAQ
Common questions about AgentMemory
Is AgentMemory open source?
Yes. The repository is listed under the Apache-2.0 license.
What is AgentMemory best for?
It is best for teams using coding agents on repositories where project context changes slowly and matters across sessions.