mirror of https://github.com/ggozad/oterm.git synced 2026-10-10 09:13:20 +02:00

the terminal client for LLMs

llm llms machine-learning ollama python terminal

Find a file

Yiorgis Gozadinos 5f4e4dd174 Merge pull request #311 from ggozad/chore/update-pydantic-ai Pydantic-ai updates in preparation for 2.0		2026-05-22 12:27:11 +03:00
.github	Build docs on pull request	2026-05-12 10:47:23 +03:00
docs	Handle additional deprecations, rename appropriately providers according to the new pydantic-ai names	2026-05-22 11:35:11 +03:00
overrides	tweaks	2026-05-11 23:04:26 +03:00
src/oterm	Drop pydantic-ai private import in test helper, type MCP log handler against public alias	2026-05-22 12:23:19 +03:00
tests	Drop pydantic-ai private import in test helper, type MCP log handler against public alias	2026-05-22 12:23:19 +03:00
.gitignore	hero	2026-05-11 22:15:37 +03:00
.pre-commit-config.yaml	Use ty/ruff	2026-04-15 12:50:20 +03:00
CHANGELOG.md	Drop pydantic-ai private import in test helper, type MCP log handler against public alias	2026-05-22 12:23:19 +03:00
codecov.yml	Reach 100% coverage by simplifying history rebuild and pragma-ing the regenerate inflight guard	2026-04-26 23:09:28 +03:00
LICENSE	Fix linter errors	2025-04-06 10:49:33 +03:00
pyproject.toml	vb	2026-05-22 11:57:07 +03:00
README.md	tweaks	2026-05-11 23:04:26 +03:00
uv.lock	vb	2026-05-22 11:57:07 +03:00
zensical.toml	tweaks	2026-05-11 23:04:26 +03:00

oterm

The terminal client for Ollama, OpenAI, Anthropic, and any pydantic-ai-supported provider.

Install

uvx oterm

Full install methods, configuration, and usage: oterm Documentation.

Multi-provider, via pydantic-ai (breaking). oterm is no longer Ollama-only — it drives any pydantic-ai-supported provider: OpenAI, Anthropic, Google (AI / Vertex), Groq, Mistral, Cohere, AWS Bedrock, DeepSeek, Cerebras, Grok, Hugging Face, OpenAI-compatible endpoints (vLLM, LM Studio, llama.cpp, OpenRouter, LiteLLM, …), and Ollama. Set the matching API key and the provider appears in the new-chat dropdown.
Refreshed chat UI. Borderless accent-driven layout, auto-growing prompt, inline [Image #N] attachment tokens, a collapsing thinking section, and a live token-usage footer in place of the spinner.
Faster streaming. Markdown is now updated as deltas arrive instead of being re-rendered on every token, so long responses don't slow the terminal as they grow.
MCP rewrite (breaking). The mcpServers config block adopts pydantic-ai's standard schema (compatible with Claude Desktop / Cursor). See docs/mcp for the full migration notes.