Name: reasonix
Author: esengine

English · 简体中文 · Website · Architecture · Benchmarks

A DeepSeek-native AI coding agent for your terminal.

Engineered around prefix-cache stability — so token costs stay low across long sessions, and you can leave it running.

Reasonix code mode — assistant proposes a SEARCH/REPLACE edit; nothing on disk until /apply

[!TIP]
Cache stability isn't a feature you turn on; it's an invariant the loop is designed around. That's the whole reason Reasonix is DeepSeek-only — every layer is tuned to the byte-stable prefix-cache mechanic.

Install

cd my-project
npx reasonix code   # paste a DeepSeek API key on first run; persists after

Requires Node ≥ 22. Tested on macOS · Linux · Windows (PowerShell · Git Bash · Windows Terminal). Get a DeepSeek API key → · reasonix code --help for flags.

What makes Reasonix different

The loop is organized around four pillars. Each one solves a problem generic agent frameworks don't even see — because they were designed for a different cache mechanic.

_{Click any card to read the full architecture writeup → Pillar 1 · Pillar 2 · Pillar 3 · Pillar 4}

Capabilities

Reasonix capabilities — cell-diff renderer, MCP, plan mode, permissions, dashboard, persistent sessions, hooks/skills/memory, semantic search, auto-checkpoints, /effort knob, transcript replay, event log

How it compares

	Reasonix	Claude Code	Cursor	Aider
Backend	DeepSeek	Anthropic	OpenAI / Anthropic	any (OpenRouter)
License	MIT	closed	closed	Apache 2
Cost profile	low per task	premium	subscription + use	varies
DeepSeek prefix-cache	engineered	not applicable	not applicable	incidental
Embedded web dashboard	yes	—	n/a (IDE)	—
Persistent per-workspace sessions	yes	partial	n/a	—
Plan mode · MCP · hooks · skills	yes	yes	yes	partial
Open community development	yes	—	—	yes

For live cache-hit rates, costs, and methodology, see benchmarks/ — the numbers move with model pricing, so they live with the harness, not in the README.

Documentation

Architecture — the four pillars, cache-first loop, harvesting, scaffolds
Benchmarks — τ-bench-lite harness, transcripts, cost methodology
Website — getting started, dashboard mockup, TUI mockup
Contributing — comment policy, error-handling rules, library-over-hand-rolled
Code of Conduct · Security policy

Community

[!NOTE]
Reasonix is open source and community-developed. The contributors wall below isn't decoration — every avatar is a real PR that shipped.

Scoped starter tickets — each with background, code pointers, acceptance criteria, and hints — live under the good first issue label. Pick anything open.

Open Discussions — opinions wanted:

#20 · CLI / TUI design — what's broken, what's missing, what would you change?
#21 · Dashboard design — react against the proposed mockup
#22 · Future feature wishlist — what would you build into Reasonix next?

Before your first PR: read CONTRIBUTING.md — short, strict rules (comments, errors, libraries-over-hand-rolled). tests/comment-policy.test.ts enforces the comment ones; npm run verify is the pre-push gate. By participating you agree to the Code of Conduct. Security issues → SECURITY.md.

Non-goals

[!IMPORTANT]
Reasonix is opinionated. Some things it deliberately doesn't do — listed here so you can pick the right tool for your work.

Multi-provider flexibility. DeepSeek-only on purpose. Coupling to one backend is the feature, not a limitation.
IDE integration. Terminal-first. The diff lives in git diff, the file tree in ls. The dashboard is a companion, not a Cursor replacement.
Hardest-leaderboard reasoning. Claude Opus still wins some benchmarks. DeepSeek is competitive on coding; if your work is "solve this PhD proof" rather than "fix this auth bug," start with Claude.
Air-gapped / fully-free. Reasonix needs a paid DeepSeek API key. For air-gapped or zero-cost runs see Aider + Ollama or Continue.

_{MIT — see LICENSE}
_{Built by the community at esengine/reasonix}