AgentToolDrop

24 of 48

Graphiti

Builds temporal knowledge graphs from agent conversations and data, tracking how facts change over time

  • score 41
  • 31.8k stars
  • 39.8 stars/day since creation
  • pushed
  • v0.31.0 on
  • Apache-2.0

Install with pip

pip install graphiti-core

Copied from the project's docs at github.com/getzep/graphiti

Why you'd want it

Graphiti turns episodes (raw text or JSON) into entities and relationships and gives each fact a validity window, so when information changes the old fact is invalidated rather than deleted and you can query what was true at any point. New data is added incrementally without recomputing the graph, and retrieval combines semantic embeddings, BM25 keyword search and graph traversal. Every fact traces back to the episode that produced it, custom entity and edge types are defined with Pydantic models, and a bundled MCP server lets assistants add and search memory.

Best for

  • Agents working on data that changes over time
  • Memory that needs provenance back to sources
  • Teams comfortable running a graph database

Use it when

You need agent memory that answers questions about relationships and history, not just similar text chunks.

Skip it if

You do not want to run a graph database: Graphiti needs Neo4j, FalkorDB or Amazon Neptune plus an LLM with structured output, OpenAI by default. Zep is the managed option from the same team, and anonymous telemetry is on by default (opt out with GRAPHITI_TELEMETRY_ENABLED=false).

Related tools

Same category or shared tags.

  1. Rank 30

    Cognee

    Memory

    Turns documents, code and conversations into a knowledge graph that agents store to and recall from

    • score 38
    • 32.3k stars
    • 28 stars/day since creation
    • pushed
    • v1.6.4 on
    • Apache-2.0

    Install with uv

    uv pip install "cognee[gliner]"
    Use it when, skip it if, stats for Cognee

    Why you'd want it

    Cognee ingests text, code and session data and builds connected memory: entities, relationships and searchable chunks for text, and a graph of symbols and dependencies for code. Its API centers on four operations (remember, recall, improve and forget), and with the gliner extra it builds and queries memory with small local CPU models and no API key, while adding an LLM key enables generated answers. It ships plugins for Claude Code and Codex, an MCP server for other clients, a REST API and Docker images for self-hosting.

    Best for

    • Agent memory across runs on your own infrastructure
    • Shared memory over docs, tickets and code
    • Local experiments without an LLM API key

    Use it when

    You want agents to keep and query project knowledge, past decisions and fixes across sessions, on infrastructure you control.

    Skip it if

    You are not on Python 3.10 to 3.14 for the library. Running the whole memory layer on a single Postgres instance is a demo feature; the production version is a licensed product.

    Stats

    New and rising score
    38 of 100
    Stars per day, since repo creation
    28
    Release
    v1.6.4,
    License
    Apache-2.0
    Pricing
    Open source
    Works with
    Claude Code, Codex, Cursor, Any MCP client, Docker
    Forks
    3,369
    Open issues
    794
    GitHub checked

    Full stat block for Cognee

  2. Rank 4

    agent-memory

    Memory

    Gives coding agents a shared long-term memory kept as plain Markdown files, with local ranked recall

    • score 68
    • 3.7k stars
    • 85.8 stars/day since creation
    • pushed
    • MIT

    Install from a checkout with uv

    git clone https://github.com/tigerless-labs/agent-memory.git
cd agent-memory
uv sync --all-packages
    Use it when, skip it if, stats for agent-memory

    Why you'd want it

    agent-memory keeps each memory as one Markdown file in a single store, with a SQLite index beside it that can be deleted and rebuilt at any time. Recall runs locally and returns a ranked list of paths with one-line abstracts, so the agent opens only what it needs, and Claude Code, Codex CLI and Muse Code can share the same store. Hooks write memories at conversation boundaries, and a separate sleep-time pass consolidates them, with deletions only arriving as proposals you confirm. It needs no API key of its own and borrows judgement from the host agent's CLI.

    Best for

    • Memory shared between Claude Code and Codex
    • Memory you can grep and keep in git
    • Agents that forget between sessions

    Use it when

    You want an agent to remember decisions across sessions and prefer a store you can read, grep and commit over an opaque database.

    Skip it if

    You want a packaged install: there is no PyPI release yet, so it installs from a git checkout with uv, and the repo was created on 2026-09-01. Setup writes lifecycle hooks into your agent's settings and runs the host agent's CLI headlessly to distil and consolidate memories.

    Stats

    New and rising score
    68 of 100
    Stars per day, since repo creation
    85.8
    License
    MIT
    Pricing
    Open source
    Works with
    Claude Code, Codex, Any MCP client
    Forks
    163
    Open issues
    56
    GitHub checked

    Full stat block for agent-memory

  3. Mem0

    Memory Standard

    Adds long-term user, session and agent memory to AI apps through a Python or TypeScript SDK

    • 67.2k stars
    • 55.4 stars/day since creation
    • pushed
    • ts-v3.3.1 on
    • Apache-2.0

    Install with pip

    pip install mem0ai
    Use it when, skip it if, stats for Mem0

    Why you'd want it

    Mem0 extracts facts from conversations with an LLM call and stores them so later turns can search them by user, session or agent. Retrieval combines semantic search, BM25 keyword matching and entity linking, with time-aware ranking for questions about current state versus past events. You can run it as a library from pip or npm, as a self-hosted server with a dashboard and API keys through Docker Compose, or on the managed Mem0 Platform.

    Best for

    • Personalized assistants and support bots
    • Remembering user preferences across sessions
    • Starting with a library and moving to a managed service later

    Use it when

    Your agent should remember facts about users or its own past actions between conversations without you designing the storage and retrieval.

    Skip it if

    You want memory with no LLM or embedding calls: Mem0 requires an LLM and defaults to OpenAI models. The README notes its benchmark scores come from the managed platform, which includes optimizations not in the open-source SDK.

    Stats

    Stars per day, since repo creation
    55.4
    Release
    ts-v3.3.1,
    License
    Apache-2.0
    Pricing
    Open source
    Forks
    7,916
    Open issues
    837
    GitHub checked

    Full stat block for Mem0

For agents

The same entry, as files an agent can read without scraping this page. 

# read one entry
curl -s https://agenttooldrop.com/tools/graphiti.md

# list the MCP servers in the catalog
curl -s https://agenttooldrop.com/tools.json \
  | jq -r '.tools[] | select(.category=="mcp-server") | .slug'