DeepSeek-Reasonix
A reliable coding agent for complex software engineering tasks.
What is DeepSeek-Reasonix?
A reliable coding agent for complex software engineering tasks.
Overview of DeepSeek-Reasonix
What it is
Reasonix is an open-source AI coding assistant. The program runs on your computer; the AI model is a service you configure, which receives what it reads. You describe a task in plain language; it reads code, edits files and runs commands and tests inside the project folder you choose, and shows you each step. You pick the model: a DeepSeek preset is built in, any OpenAI-compatible service is one config entry, and you pay the model provider directly.
Key features
- Read, edit, run. It reads code, edits files and runs tests and commands, all inside your project folder.
- Permission levels. Have it ask every time, or let everyday actions run on their own; your forbid rules always hold. Plan mode starts work only once you approve.
- Rewind. A file is saved before it changes, so you can rewind by conversation turn without touching your git history. Only files its edit tools changed are covered.
- Config-driven. Providers, the agent, enabled tools, and plugins are all declared in
reasonix.toml. No hardcoded models. - Multi-model & composable. DeepSeek ships as a preset; any OpenAI-compatible endpoint is a config entry. Optionally run two models together (executor + planner) in separate, cache-stable sessions.
- Plugin-driven. MCP servers contribute tools, prompts, and resources; Extension Protocol v1 sidecars can intercept runtime events, contribute Providers and structured UI, and ship versioned plugin packages.
- Zero-friction distribution.
CGO_ENABLED=0single binary; cross-compile to six targets with one command. The result is a fully self-contained static binary.
Use cases
Reasonix is designed for complex software engineering tasks. It can read project code, edit files, run tests, and execute shell commands. Example use cases include adding retry logic to an HTTP client, automating code refactoring, running test suites, and managing project configurations. It can also be used as a subagent from DeepSeek Harness via the Agent Client Protocol (ACP).
Getting started
Download and install the Reasonix Studio desktop app from the releases page, or use the command-line tool. For the terminal:reasonix setupreasonixFor the desktop app: open it, enter your model provider and key when asked, open your project folder, and write your task. See the repository README for detailed installation and quick start instructions.
License and pricing
License: MIT. Pricing: open source (free). The project is open source and runs on your computer; you pay the model provider directly for AI service usage.
Based on the project's public README and repository metadata.