Eclipse extension that provides inline completion backed by LLMs
Codex Skill fork of fast-context-mcp that calls Windsurf Devstral without an MCP server
Docker service stack for a comprehensive local ai experience, running on a normal home hardware setup with single GPU. Project-Status: Working, Backlog.
OpenAI-compatible proxy that makes local LLM tool calling actually work — schema validation, retry with feedback, model escalation, and context condensing
17 agent profiles for Mistral Vibe 2.5.0. Checked against the loader itself, because a broken profile fails silently.
OllamaLLM Desktop App. Golang API. Utilizes 10 LLMs. ChatGPT-like GUI . In it's current form, it operates as a desktop app / local host API, but, has the foundation to be scaled up to become a complete web app. See the documentation for more.
The open-source agentic coding CLI. Focused on Ollama Cloud Models.
EU-sovereign multi-model LLM serving pipeline — Apertus 70B + Devstral 24B + EuroLLM 22B with EU AI Act Art. 52/53 transparency
137 Agent Skills for Mistral Vibe. Generated, flat because discovery does not recurse, and shipped with a checker that has its own tests.
27 one-shot FR agents on Mistral La Plateforme — Large, Ministral, Devstral, Pixtral, zero-429
Open-source terminal AI coding agent on Mistral (Devstral/Codestral). Claude Code-style CLI with MCP, subagents, hooks, sessions, web tools, permissions & cost tracking.
Autonomous dev agent that runs on your hardware. No cloud. No API keys. Ships code while you sleep.
14 one-shot coding agents on Mistral La Plateforme — Devstral + Codestral, zero-429
To associate your repository with the devstral topic, visit your repo's landing page and select "manage topics."