letta vs ollama
A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.
| letta | ollama | |
|---|---|---|
| Tagline | Platform for stateful agents with advanced memory and self-improvement capabilities. | Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. |
| Stars | 24k | 176k |
| Forks | 2.5k | 17k |
| Open issues | 48 | 3.4k |
| Language | Python | Go |
| License | Apache-2.0 | MIT |
| Last pushed | Jul 3, 2026 | Jul 7, 2026 |
| Categories | AI Agents | AI Agents, LLM Frameworks |
letta
Letta is a platform designed to build AI agents that can operate in a persistent, memory-rich environment, enabling them to learn from past interactions and improve over time. It supports both local execution via CLI tools and integration into applications using the SDK. Agents can run on Letta's server or self-hosted infrastructure.
Python
ollama
Ollama is a platform for deploying and interacting with various large language models (LLMs) such as Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, and Gemma on macOS, Windows, Linux, and Docker environments.
Go