head to head · open source

graphify vs Letta

graphify has 118,991 GitHub stars, 11,505 forks, 1,350 open issues and last shipped 2 days ago. Letta has 3,366 stars, 411 forks, 347 open issues and last shipped yesterday. graphify leads on adoption by 3,435% (118,991 vs 3,366 stars). graphify is written in Python under Apache-2.0; Letta is written in TypeScript under Apache-2.0. graphify has attracted 10% as many forks as stars, Letta 12%. Letta was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 1 topic tag (codex), so they are genuine substitutes rather than adjacent tools.

Two open source projects, one decision. Both are free and self-hostable — the differences are community size, license terms, language stack and release pace.

graphify ★ 119K Letta ★ 3.4K category AI & Machine Learning

← all 8884 open source comparisons

Side by side

graphify Letta
GitHub stars ★ 119K ★ 3.4K
License Apache-2.0 Apache-2.0
Written in Python TypeScript
Last push 2026-09-16 2026-09-17
Forks ⑂ 12K ⑂ 411
Self-hosting Yes Yes
Data ownership Your server Your server

pick graphify if

  • You weight community size — 119K stars and counting
  • You want the Apache-2.0 license terms
  • Your stack matches Python
  • You value the larger contributor base for long-term maintenance

full graphify profile →

pick Letta if

  • You want the Letta feature set and don't need the biggest community
  • You prefer the Apache-2.0 license terms
  • Your stack matches TypeScript
  • You evaluated both and Letta fits your workflow better

full Letta profile →

About graphify

graphify is an Apache 2.0 Python CLI and /graphify skill that turns a whole project — code, docs, SQL schemas, configs, PDFs, images, and video — into a queryable knowledge graph, built for developers and AI agent users in Claude Code, Cursor, Codex, and Gemini CLI who want to query a codebase instead of grepping through files.

read the full graphify overview →

About Letta

Letta Code is an open source TypeScript harness under Apache 2.0 for stateful AI agents. It lives in the AI & Machine Learning / AI Development Platforms ecosystem. It gives agents memory, identity, and a sense of experience over time. It targets agents that behave more like people than tools.

read the full Letta overview →

More in AI & Machine Learning

OpenClaw ★ 390K Hermes Agent ★ 246K Ollama ★ 181K Dify ★ 156K Open WebUI ★ 152K langchain ★ 147K

Related comparisons

dify vs graphify langchain vs graphify ponytail vs graphify dify vs langchain dify vs ponytail langchain vs ponytail dify vs claude-mem dify vs ragflow openclaw vs hermes-agent openclaw vs open-webui openclaw vs lobechat openclaw vs anythingllm openclaw vs cherry-studio openclaw vs nanobot openclaw vs jan openclaw vs librechat ollama vs llama-cpp ollama vs vllm ollama vs gpt4all ollama vs llama-index ollama vs localai llama-cpp vs vllm ollama vs pageindex ollama vs langfuse

More AI Development Platforms projects

Compare either of these against the rest of the AI Development Platforms field.

graphify vs Dify graphify vs langchain graphify vs ponytail graphify vs generative-ai-for-beginners graphify vs claude-mem graphify vs ragflow graphify vs PaddleOCR graphify vs Agent-Reach graphify vs headroom graphify vs Mem0 graphify vs daily_stock_analysis graphify vs LiteLLM

Frequently asked questions

Is graphify or Letta more popular?

graphify has 118,991 GitHub stars and Letta has 3,366. graphify has the larger community by that measure.

Are graphify and Letta free?

Both are open source. graphify is licensed under Apache-2.0 and Letta under Apache-2.0. Neither carries a licence fee.

What is the difference between graphify and Letta?

graphify is written in Python and Letta in TypeScript. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.

Which should I choose, graphify or Letta?

Choose graphify if you want the larger community (118,991 stars) or its Apache-2.0 licence terms. Choose Letta if its feature set, stack or Apache-2.0 licence fits better. Both are self-hostable.