ChatOllama

An open-source agentic command-line app for running AI agents against local or hosted language models from providers such as OpenAI, Anthropic, Gemini, DeepSeek and Ollama.

Visit website github.com

ChatOllama is an open-source agentic application for running AI agents with hosted or local models. Its primary entry point is the chatollama-agent command-line app, installed globally with npm and requiring Node.js 24 or newer.

Provider credentials are set through environment variables such as OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY or DEEPSEEK_API_KEY, and startup overrides let a user choose a specific provider and model, override an endpoint or credential, or set a per-prompt step budget. Ollama is supported as one OpenAI-compatible provider among the others, and the CLI falls back to a local Ollama model when no other model is configured or reachable.

It is written in TypeScript.

More in Agent frameworks

See all 902

Recurse
recurse.run
A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.
- Agent frameworks
ProofForge
shulgin.is-a.dev
An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.
- Agent frameworks
local-coder
github.com
Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.
- Coding agents
- Agent frameworks

More in Agent frameworks

Recurse

ProofForge

local-coder

Cookies