Runs a DeepSeek-first coding agent in the terminal, a desktop studio, or VS Code, with cache-aware context handling and other OpenAI-compatible providers via config.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your coding agent:
- Planner And Executor
Use Reasonix to run two models together as an executor and a planner: ‹what you need›
- MCP Plugins
Use Reasonix to add tools, prompts, and resources from MCP servers: ‹what you need›
- Editor Integration
Use Reasonix to run a local reasonix acp backend: ‹what you need›
Install the CLI
Install it as its own instructions say.
Its page: github.com/esengine/DeepSeek-Reasonix
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- CLI
- Auth
- API Key
- Skills
- 5
Skills
Config-Driven Providers
Declares providers, the agent, tools, and plugins in reasonix.toml, with DeepSeek as a preset and other endpoints as config.
Planner And Executor
Runs two models together as an executor and a planner in separate, cache-stable sessions on the same task.
Cache-Aware Context
Injects a small stable environment summary and prunes stale tool output before summary compaction to keep caches warm.
MCP Plugins
Adds tools, prompts, and resources from MCP servers, plus Extension Protocol sidecars that intercept runtime events.
Editor Integration
Runs a local reasonix acp backend that the VS Code extension uses for chat, editor context, and tool-call approvals.