# AgentMemory

Persistent memory for AI coding agents, with benchmarks and local-first workflows.

## Agent Decision Summary
- Risk level: elevated
- Source confidence: high
- Recommended workflows: Coding agent workflow, Local or private AI stack, Memory or RAG workflow
- Permission surface: shell/files, memory
- Agent JSON: https://www.openagent.bot/memory-systems/agentmemory.agent.json

## Summary
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.


## Guide
AgentMemory is an open-source persistent memory layer for AI coding agents.

### 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 it works
Start with one repository, store a small set of durable facts, and compare future agent sessions with and without the memory layer.


### FAQ
- 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.
## What It Does
It gives coding agents a place to store project knowledge that should survive beyond a single chat or task.

## How To Evaluate
Start with one repository, store a small set of durable facts, and compare future agent sessions with and without the memory layer.

## Why It Matters
Coding agents lose a lot of value when they forget repository conventions and prior decisions. AgentMemory targets that gap with a dedicated memory layer for developer workflows.


## Best For
- 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

## Not For
- Teams that only need vector search for documents
- Users who do not want agents retaining project context between sessions

## What It Actually Does
- Coding-agent focus: AgentMemory is framed around coding assistants rather than generic chatbot memory.
  - Why it matters: 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.
  - Why it matters: Persistent context reduces repeated onboarding and makes long projects less fragile.
- Benchmark-oriented positioning: The project emphasizes real-world memory benchmarks for coding agents.
  - Why it matters: Memory products are easy to overclaim; benchmarks help teams inspect actual workflow impact.

## Typical Use Cases
- 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.

## 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.

## Fit Matrix
- Coding agent workflow: strong. AgentMemory has multiple signals for coding agent workflow, including matching tags, capabilities, category, or positioning. Required check: Run a small repository change and inspect the diff, tests, and rollback path.
- Local or private AI stack: strong. AgentMemory has multiple signals for local or private ai stack, including matching tags, capabilities, category, or positioning. Required check: Verify hardware requirements, data path, storage, and whether all calls stay in your environment.
- Memory or RAG workflow: strong. AgentMemory has multiple signals for memory or rag workflow, including matching tags, capabilities, category, or positioning. Required check: Create, update, retrieve, correct, and delete memory or retrieval objects with real data.
- Evaluation and observability: partial. AgentMemory has at least one signal for evaluation and observability, but should be checked against a real task before adoption. Required check: Add one repeatable test case and confirm results can run again in review or CI.
- Reusable skill workflow: partial. AgentMemory has at least one signal for reusable skill workflow, but should be checked against a real task before adoption. Required check: Run one skill end to end and check whether it produces evidence or structured output.
- Browser automation: weak. AgentMemory is not primarily positioned for browser automation in the current metadata. Required check: Run one non-sensitive website task and inspect clicks, waits, retries, and changed URLs.

## Evidence
- verified: AgentMemory is listed as open source. Source: License metadata: Apache-2.0
- verified: AgentMemory has a recorded GitHub repository: rohitg00/agentmemory. Source: Resource facts and GitHub source link.
- inferred: AgentMemory supports these recorded deployment modes: cloud. Source: OpenAgent decision signal metadata.
- inferred: AgentMemory is tagged with memory capabilities. Source: OpenAgent capability taxonomy.

## Missing Checks
- Dedicated docs link is missing.
- Repository freshness has not been recorded.

## Next Actions
- Inspect repository: https://github.com/rohitg00/agentmemory
- Open Homepage: https://agent-memory.dev

## Facts
- Category: memory-systems
- Resource type: memory_system
- Open source: yes
- License: Apache-2.0
- Last verified: 2026-06-09
- GitHub repo: rohitg00/agentmemory
- GitHub stars: 22013

## Capabilities
- memory

## Structured Use Case Tags
- personal-memory

## Getting Started
- Open the GitHub repository: https://github.com/rohitg00/agentmemory
- Visit the project website: https://agent-memory.dev

## Links
- GitHub: https://github.com/rohitg00/agentmemory
- Homepage: https://agent-memory.dev

## Structured Outputs
- JSON: https://www.openagent.bot/memory-systems/agentmemory.json
- Markdown: https://www.openagent.bot/memory-systems/agentmemory.md
- Agent JSON: https://www.openagent.bot/memory-systems/agentmemory.agent.json
- Canonical: https://www.openagent.bot/memory-systems/agentmemory