# rohitg00/agentmemory

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/rohitg00-agentmemory).**

23,785 stars · 1,959 forks · TypeScript · Apache-2.0

## Links

- GitHub: https://github.com/rohitg00/agentmemory
- Homepage: https://agent-memory.dev
- awesome-repositories: https://awesome-repositories.com/repository/rohitg00-agentmemory.md

## Topics

`agentmemory` `agents` `ai` `claude` `claudecode` `codex` `copilot` `cursor` `genai` `harness` `hermes` `memory` `openclaw`

## Description

AgentMemory is a persistent knowledge store and memory server designed to provide AI coding agents with long-term memory. It functions as a knowledge graph engine and vector database store that saves and recalls project context, architectural decisions, and patterns across different sessions.

The system distinguishes itself by using a tiered-memory consolidation pipeline that compresses raw observations into episodic, semantic, and procedural layers to optimize token usage. It employs a hybrid retrieval strategy combining keyword matching, vector embeddings, and graph traversal to surface relevant historical context.

The project covers a broad range of capabilities including automated project observation via lifecycle hooks, multi-agent coordination through shared synchronized memory pools, and local-first vector storage for data privacy. It also provides an interface for the Model Context Protocol to expose memory tools to compatible agents.

The system includes a command-line interface for server runtime management and environment bootstrapping.

## Tags

### Artificial Intelligence & ML

- [Agent Memory Persistence](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-memory-persistence.md) — Provides a long-term knowledge store for AI coding agents to maintain continuity across project sessions.
- [Agent Memory Server Runtimes](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-memory-server-runtimes.md) — Runs the persistent knowledge store and manages the runtime engine that enables long-term agent memory. ([source](https://agent-memory.dev/docs/reference/cli))
- [Agent Activity Observers](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-activity-observers.md) — Automatically captures agent tool use and file operations through hooks to build a long-term knowledge store.
- [Long-term Memory Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/memory-management-systems/long-term-memory-stores.md) — Implements a pipeline that compresses raw observations into long-term memory stores to reduce token costs.
- [Fact Extraction Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/memory-management-systems/long-term-memory-stores/fact-extraction-pipelines.md) — Implements pipelines that process raw session data to isolate and store confirmed facts into long-term memory. ([source](https://agent-memory.dev/docs/concepts/memory-types))
- [Multi-Agent Coordination Systems](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/orchestration-engines/ai-agent/multi-agent-coordination-systems.md) — Manages task distribution across agents by tracking actionable work items, dependencies, and priorities. ([source](https://agent-memory.dev/docs/guides/team-memory))
- [Agent Communication Protocols](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-communication-protocols.md) — Implements standardized protocols to connect AI agents to the persistent memory server for project data retrieval. ([source](https://agent-memory.dev/docs/connect-agents))
- [Hybrid Search Retrievers](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-rag-development/knowledge-base-retrieval/hybrid-search-retrievers.md) — Combines keyword matching, vector embeddings, and graph traversal to retrieve the most relevant project context.
- [Three-Tier Memory Architectures](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/memory-context-systems/agent-memory-architectures/composable-memory-architectures/three-tier-memory-architectures.md) — Organizes raw observations into episodic, semantic, and procedural memory tiers to optimize token usage.
- [Model Context Protocol Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-assistant-integrations/model-context-protocol-integrations.md) — Provides standardized MCP tools that allow agents to explicitly save and analyze project patterns. ([source](https://agent-memory.dev/docs/integrations/claude-code))
- [Automated Activity Observation](https://awesome-repositories.com/f/artificial-intelligence-ml/automated-activity-observation.md) — Automatically records file edits and tool calls using lifecycle hooks to build a project knowledge base.
- [Automatic Memory Extractors](https://awesome-repositories.com/f/artificial-intelligence-ml/automatic-memory-extractors.md) — Automatically extracts and records project details from agent activities without requiring manual user commands. ([source](https://agent-memory.dev/docs/integrations/copilot))
- [Context Compression](https://awesome-repositories.com/f/artificial-intelligence-ml/context-compression.md) — Compresses observations and injects relevant context into the agent's prompt based on the available token budget. ([source](https://agent-memory.dev/docs/llms.txt))
- [Knowledge Graph Extraction](https://awesome-repositories.com/f/artificial-intelligence-ml/knowledge-graph-extraction.md) — Identifies entities and relationships within stored memories to enable context recall through graph traversal.
- [Semantic Context Stores](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-inference-serving/request-routing-gateways/semantic-context-stores.md) — Utilizes vector-based storage to manage compressed project state and retrieve context via semantic search.
- [MCP Servers](https://awesome-repositories.com/f/artificial-intelligence-ml/mcp-servers.md) — Exposes memory capabilities as a standardized Model Context Protocol server for compatible AI agents. ([source](https://cdn.jsdelivr.net/gh/rohitg00/agentmemory@main/README.md))
- [Memory Compression](https://awesome-repositories.com/f/artificial-intelligence-ml/memory-compression.md) — Summarizes incoming observations into condensed memories using language models to minimize token usage. ([source](https://agent-memory.dev/docs/guides/configuration))
- [Memory Retrieval Budget Controllers](https://awesome-repositories.com/f/artificial-intelligence-ml/reasoning-token-budgeting/reasoning-budget-controllers/memory-retrieval-budget-controllers.md) — Limits the amount of recalled memory injected into prompts to optimize token consumption.
- [Vector Embeddings](https://awesome-repositories.com/f/artificial-intelligence-ml/vector-embeddings.md) — Generates vector representations of text using local or cloud providers to enable semantic retrieval. ([source](https://agent-memory.dev/docs/guides/llm-providers))
- [RESTful Memory Administration APIs](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/memory-management-systems/long-term-memory-stores/hybrid-short-and-long-term-memory/graph-structured-memory-apis/restful-memory-administration-apis.md) — Provides programmatic endpoints to save, recall, forget, or export memory entries and manage active sessions. ([source](https://agent-memory.dev/docs/llms.txt))
- [Message-Passing Agent Orchestrators](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/orchestration-engines/ai-agent/multi-agent-coordination-systems/message-passing-agent-orchestrators.md) — Coordinates AI agents through a central hub where they exchange structured signals and messages in real time. ([source](https://agent-memory.dev/docs/guides/team-memory))
- [Role and Context Isolation](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/orchestration-engines/ai-agent/multi-agent-coordination-systems/role-and-context-isolation.md) — Tags and filters memory by role to share knowledge or isolate data between different agents. ([source](https://cdn.jsdelivr.net/gh/rohitg00/agentmemory@main/README.md))
- [Agent Monitoring](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-monitoring.md) — Monitors the lifecycle and interactions of sub-agents to capture distributed tasks. ([source](https://agent-memory.dev/docs/concepts/how-memory-works))
- [Model Provider Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-systems-frameworks/model-integration-serving/ai-model-orchestration/model-provider-integrations.md) — Integrates with cloud and local model providers to perform data compression and knowledge extraction. ([source](https://agent-memory.dev/docs/llms.txt))
- [Action Approval Gates](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-action-frameworks/action-approval-gates.md) — Pauses agent task execution at specific checkpoints to request human approval before proceeding. ([source](https://agent-memory.dev/docs/guides/team-memory))
- [File-Centric History Retrieval](https://awesome-repositories.com/f/artificial-intelligence-ml/conversational-session-management/multi-session-context-synthesizers/session-history-retrieval/file-centric-history-retrieval.md) — Collects all recorded edits and decisions associated with a specific file from earlier sessions. ([source](https://agent-memory.dev/docs/integrations/cursor))
- [Local AI Runtimes](https://awesome-repositories.com/f/artificial-intelligence-ml/local-ai-runtimes.md) — Runs memory servers and embedding models on local hardware to ensure data privacy.
- [Offline Model Runners](https://awesome-repositories.com/f/artificial-intelligence-ml/local-model-serving/offline-model-runners.md) — Enables fully offline operation using local embedding and model servers to ensure data privacy. ([source](https://agent-memory.dev/docs/guides/llm-providers))
- [Multi-Agent Coordination](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-agent-coordination.md) — Synchronizes a shared memory pool and task dependencies across multiple autonomous agents.
- [Pinned Context Slots](https://awesome-repositories.com/f/artificial-intelligence-ml/pinned-context-slots.md) — Provides dedicated, editable slots for persisting personas and guidelines that agents can reference. ([source](https://agent-memory.dev/docs/guides/configuration))

### Part of an Awesome List

- [Memory Pattern Extraction](https://awesome-repositories.com/f/awesome-lists/ai/reasoning-frameworks/cognitive-reasoning-patterns/memory-pattern-extraction.md) — Analyzes stored memories to extract recurring cognitive patterns and project insights to update architectural context. ([source](https://agent-memory.dev/docs/guides/configuration))
- [AI Skills](https://awesome-repositories.com/f/awesome-lists/ai/ai-skills.md) — Persistent memory solutions for coding agents.

### Data & Databases

- [Knowledge Graphs](https://awesome-repositories.com/f/data-databases/entity-relationships/knowledge-graphs.md) — Extracts entities and relationships into a graph structure to enable context recall through traversal.
- [Agent Memory Stores](https://awesome-repositories.com/f/data-databases/entity-relationships/knowledge-graphs/agent-memory-stores.md) — Functions as a persistent memory store that exposes project context to agents via a standardized server.
- [Graph Traversal](https://awesome-repositories.com/f/data-databases/graph-traversal.md) — Identifies related memories by traversing a graph of entities to surface connections between files and decisions. ([source](https://agent-memory.dev/docs/concepts/search))
- [Hybrid Memory Stores](https://awesome-repositories.com/f/data-databases/hybrid-memory-stores.md) — Implements a hybrid retrieval mechanism combining keywords and vectors specifically for AI agent memory. ([source](https://agent-memory.dev/docs/introduction))
- [Vector Storage](https://awesome-repositories.com/f/data-databases/local-first-storage/vector-storage.md) — Persists embeddings and indices locally on the machine to ensure data privacy and reduce API costs.
- [Multi-Tier Memory Systems](https://awesome-repositories.com/f/data-databases/tiered-caching-systems/multi-tier-memory-systems.md) — Organizes agent experiences into episodic, semantic, and procedural tiers to optimize detail and token usage. ([source](https://cdn.jsdelivr.net/gh/rohitg00/agentmemory@main/README.md))
- [Vector Databases](https://awesome-repositories.com/f/data-databases/vector-databases.md) — Provides a vector database for storing high-dimensional embeddings of project observations and facts.
- [Activity Observation Recording](https://awesome-repositories.com/f/data-databases/vector-memory-stores/memory-optimized-storage/memory-record-creators/activity-observation-recording.md) — Records file operations, shell commands, and agent decisions to build a long-term history of observations. ([source](https://agent-memory.dev/docs/concepts/how-memory-works))
- [Vector Search](https://awesome-repositories.com/f/data-databases/vector-search.md) — Retrieves historical observations based on conceptual similarity using embedding vectors and cosine similarity. ([source](https://agent-memory.dev/docs/concepts/search))
- [Embedded Storage Engines](https://awesome-repositories.com/f/data-databases/data-engineering-infrastructure/data-persistence-storage/data-storage/file-based-storage/embedded-storage-engines.md) — Utilizes a local embedded storage engine to keep observations and indices on the local machine for privacy. ([source](https://agent-memory.dev/docs/introduction))
- [Execution Collision Preventers](https://awesome-repositories.com/f/data-databases/duplicate-detection-tools/atomic-duplicate-prevention/execution-collision-preventers.md) — Uses locking mechanisms to prevent multiple agents from executing the same task simultaneously. ([source](https://agent-memory.dev/docs/guides/team-memory))
- [Keyword Search](https://awesome-repositories.com/f/data-databases/search-indexing-technologies/search-indexing/search-information-retrieval/matching-ranking-logic/keyword-search.md) — Implements text-based search using term frequency and synonym expansion to match exact technical terms. ([source](https://agent-memory.dev/docs/concepts/search))
- [Search Result Fusion Algorithms](https://awesome-repositories.com/f/data-databases/search-result-fusion-algorithms.md) — Combines and re-ranks results from multiple search methods to provide diversified and relevant context. ([source](https://agent-memory.dev/docs/concepts/search))

### Software Engineering & Architecture

- [Persistent Project Artifacts](https://awesome-repositories.com/f/software-engineering-architecture/project-context-managers/persistent-project-artifacts.md) — Persists architectural decisions and naming conventions as managed artifacts to maintain project context across sessions. ([source](https://agent-memory.dev/docs/integrations/copilot))
- [Team Memory Synchronization](https://awesome-repositories.com/f/software-engineering-architecture/project-management-governance/repository-maintenance/project-organization/git-repository-synchronizers/memory-synchronizers/team-memory-synchronization.md) — Synchronizes a shared knowledge store across multiple users and agents using a team identifier. ([source](https://agent-memory.dev/docs/guides/team-memory))
- [Shared Knowledge Graph Memory](https://awesome-repositories.com/f/software-engineering-architecture/shared-memory-management/shared-knowledge-graph-memory.md) — Provides a shared knowledge graph where multiple agents can read and write common patterns with session-level isolation. ([source](https://agent-memory.dev/docs))

### User Interface & Experience

- [LLM Context Window Injections](https://awesome-repositories.com/f/user-interface-experience/design-token-synchronization/prompt-context-synchronization/llm-context-window-injections.md) — Automatically populates agent prompts with relevant historical context while respecting token budget constraints. ([source](https://agent-memory.dev/docs/guides/configuration))

### Development Tools & Productivity

- [Task Dependency Filters](https://awesome-repositories.com/f/development-tools-productivity/task-dependency-filters.md) — Retrieves high-priority tasks by filtering for those whose dependencies have been met. ([source](https://agent-memory.dev/docs/guides/team-memory))

### System Administration & Monitoring

- [Agent Execution Replays](https://awesome-repositories.com/f/system-administration-monitoring/ai-session-monitoring/session-replays/agent-execution-replays.md) — Visualizes a timeline of prompts and tool calls with playback controls to audit agent activities. ([source](https://cdn.jsdelivr.net/gh/rohitg00/agentmemory@main/README.md))