@NFTCPS: 卧槽!DeepSeek 这波是要把市面上的 Agent 一锅端啊,全家桶都给你凑齐了! 连 Reasonix 都没放过,直接收编。 跟你们说人话: 这玩意儿是目前最能帮你省 DeepSeek 账单的原生终端 工具调用稳得一批,不抽风 靠缓…
摘要
DeepSeek-Reasonix 是一个基于 DeepSeek 的原生终端 AI 编码代理,通过缓存命中大幅降低 API 成本,工具调用稳定可靠。
查看缓存全文
缓存时间: 2026/05/26 07:03
卧槽!DeepSeek 这波是要把市面上的 Agent 一锅端啊,全家桶都给你凑齐了!
连 Reasonix 都没放过,直接收编。
跟你们说人话:
这玩意儿是目前最能帮你省 DeepSeek 账单的原生终端 工具调用稳得一批,不抽风 靠缓存命中直接把 API 价格砍到脚踝,骨折都不够形容
钱包不疼的感觉,谁用谁知道。
https://github.com/esengine/deepseek-reasonix…
esengine/deepseek-reasonix
Source: https://github.com/esengine/deepseek-reasonix
English · 简体中文 · Website · Guide · Architecture · Benchmarks · Discord
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.
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.
Real user, single day (2026-05-01): 435M input tokens, 99.82% cache hit, ~12 instead of the ~61 the same workload would cost with no cache on
v4-flash— see the case study. DeepSeek provides the cacheable bytes; the four mechanisms in Pillar 1 are how Reasonix keeps them cacheable across long sessions.
Community · 加入社区 — bilingual Discord with channels for setup help (
#help/#求助), workflow showcases, feature ideas, and contributor-only PR coordination. Verify your GitHub in-server to get the Contributor role automatically. → https://discord.gg/XF78rEME2D
Install
Requires Node ≥ 22. Works on macOS · Linux · Windows (PowerShell · Git Bash · Windows Terminal).
Install Reasonix globally if you want the reasonix command available on your PATH:
npm install -g reasonix
reasonix code my-project # paste a DeepSeek API key on first run; persists after
Or run it once without installing globally:
cd my-project
npx reasonix code # always uses the latest package by default
Grab a DeepSeek API key → · reasonix code --help for flags.
If you use Reasonix daily, global install is the simplest path. If you just want to try it, use npx.
Prefer fewer keystrokes? The shorter dsnix alias resolves to the same CLI:
npm install -g dsnix # exposes `dsnix` on PATH, depends on reasonix
npx dsnix@latest code # one-shot via the shorter command
A global npm install -g reasonix also drops a dsnix shim on PATH, so the two are interchangeable.
Bare reasonix (no subcommand) launches code in the current directory — typing reasonix and reasonix code are equivalent.
| Command | When |
|---|---|
reasonix / reasonix code [dir] | The coding agent. Start here. |
reasonix chat | Plain chat — no filesystem or shell tools. |
reasonix run "task" | One-shot, streams to stdout. Good for pipes. |
reasonix doctor | Health check: Node, API key, MCP wiring. |
reasonix update | Upgrade Reasonix itself. |
Other subcommands (replay · diff · events · stats · index · mcp · prune-sessions) are in reasonix --help and the CLI reference.
QQ channel
QQ can extend an existing chat, code, or desktop session as a remote channel. It is part of the current session flow, not a separate runtime mode.
- CLI: start a session, then run
/qq connect - Desktop: open
Settings -> General -> QQ Channel
Once connected, QQ messages can enter the current session, assistant replies route back to QQ, and follow-up interactions can continue remotely.
For full setup, desktop quick start, and troubleshooting, see QQ channel setup.
Desktop client (prerelease)
A native Tauri client for users who want a GUI over the same loop. Multi-tab, the right-panel shows files the agent has read or edited this session, the same cost / cache / token meters live at the bottom. Same DeepSeek API key, same ~/.reasonix config — the desktop bundles its own Node runtime, no separate npm install step.
Download platform installers from GitHub Releases. The desktop ships as a prerelease: the loop and protocol are the same as the CLI, but the UI is still being polished and the installers aren’t code-signed yet.
- macOS — first launch hits Gatekeeper. One-time fix:
xattr -dr com.apple.quarantine /Applications/Reasonix.app(or right-click → Open → confirm). - Windows — SmartScreen warns “Unknown publisher”. Click More info → Run anyway.
- Linux —
.deband.AppImageship plain, no extra step.
The CLI remains the canonical surface. Anything that lands in the CLI is also available from the desktop’s composer.
Working in another folder · chat vs. code · author a skill
Working in a different folder. Reasonix scopes filesystem tools to the launch directory; pass --dir to retarget. Mid-session switching isn’t supported by design (memory paths would tangle with stale roots) — quit and relaunch.
npx reasonix code --dir /path/to/project
Picking chat vs code. code is the default and the only mode with filesystem / shell tools and SEARCH/REPLACE review. chat is the lighter, tools-off shell — reach for it when you want a thinking partner with MCP attached but no disk access.
| What you get | code | chat |
|---|---|---|
Filesystem tools + edit_file | ✓ | — |
SEARCH/REPLACE → /apply review | ✓ | — |
| Shell tool (gated) | ✓ | — |
Plan mode · /todo · /skill new · /mcp add | ✓ | — |
Memory (remember / recall_memory) | project + global | global only |
MCP servers from config · web search · ask_choice | ✓ | ✓ |
| Coding system prompt | ✓ | generic |
| Session scope | per-directory | shared default |
Author your first skill. No remote registry — write them directly. Edit the file (description: frontmatter + body), then /skill list. Add runAs: subagent to spawn an isolated subagent loop instead of inlining the body.
/skill new my-skill # <project>/.reasonix/skills/my-skill.md
/skill new my-skill --global # ~/.reasonix/skills for cross-project use
Claude-format skills also load. <project>/.claude/skills/<name>/SKILL.md and ~/.claude/skills/ are read alongside Reasonix’s native paths, so tooling that emits Claude-format skills works out of the box. Example — drop OpenSpec workflows in without an upstream adapter:
npx openspec init --tools claude # writes .claude/skills/openspec-*/SKILL.md
/skill openspec-propose <task> # then invoke from Reasonix
Configuration
One JSON file at ~/.reasonix/config.json plus per-project overrides under <project>/.reasonix/. The full bilingual reference — every key, every slash command, the on-disk shape of skills/memory/hooks — lives at:
| Topic | Quick read |
|---|---|
| MCP servers | stdio · SSE · Streamable HTTP. One spec format works for both config.json and --mcp. |
| Skills | Markdown playbooks the model can invoke. inline or subagent mode. |
| Memory | User-private knowledge pinned into the prefix. user / feedback / project / reference types. |
| Hooks | Shell commands on lifecycle events. PreToolUse (gating) · PostToolUse · UserPromptSubmit · Stop. |
| Permissions | Per-workspace shell allowlist. Exact-prefix match. |
| Web search | Mojeek by default; switch to self-hosted SearXNG or Metaso with /search-engine. |
| Semantic index | reasonix index — local Ollama or any OpenAI-compatible embedding endpoint. |
What makes Reasonix different
The loop is organized around three pillars. Each one solves a problem generic agent frameworks don’t even see — because they were designed for a different cache mechanic.
Click through to the full architecture writeup → Pillar 1 — Cache-first loop · Pillar 2 — Tool-call repair · Pillar 3 — Cost control
Capabilities
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) | — |
| Configurable web search engine | /search-engine | — | — | — |
| Persistent per-workspace sessions | yes | partial | n/a | — |
| Plan mode · MCP · hooks · skills | yes | yes | yes | partial |
| Web search (Mojeek + SearXNG + Metaso) | yes | yes | yes | yes |
| 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 — three pillars: cache-first loop, tool-call repair, cost control
- CLI Reference — every shell subcommand, every slash command, every keybinding
- QQ channel setup — CLI first-connect flow, desktop entry, and QQ Open Platform credentials
- 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
Reasonix is open source and community-developed. Every avatar in the Acknowledgments wall at the bottom of this file 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?
Already using Reasonix and willing to help others discover it? Publish blog posts, articles, screenshots, talks, or videos to Show and tell. The project has no marketing budget — community word of mouth is how new users find it. Sustained advocates earn the badge below, displayed next to the contributors wall once awarded:
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
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 inls. 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.
Star History
Support
If Reasonix has been useful and you’d like to say thanks, you can. It stays a coffee, not a contract — donations don’t buy feature priority or change how issues get triaged.
- International — PayPal: paypal.me/yuhuahui
- 国内 — 微信支付(扫码)
Acknowledgments
A small list of folks whose work has shaped Reasonix the most — measured by both commit count and code volume. Listed alphabetically, no ordering of importance. The full contributor graph is on GitHub.
- ctharvey
- dimasd-angga (Dimas D. Angga)
- Evan-Pycraft
- ForeverYoungPp
- GTC2080 (TaoMu)
- kabaka9527
- lisniuse (Richie)
- wade19990814-hue
- wviana (Wesley Viana)
Also a separate thank-you to Bernardxu123
for designing the project logo (see docs/brand/), and to
AIGC Link for promoting the project on XiaoHongShu.
MIT — see LICENSE
Built by the community at esengine/DeepSeek-Reasonix
鸟哥 | 蓝鸟会🕊️ (@NFTCPS): 兄弟们,AI Agent 这玩意儿你还在零散学?看这个!
22章骨架课程,专门教你怎么从0到1搭一套生产级的 Agent 系统👇
1️⃣ 工具调用、Agent 循环、记忆系统 2️⃣ 多 Agent 协作、人机交互 3️⃣ 后端架构、可观测性、成本优化、安全防护
最骚的是核心玩法——用 Agent 学
相似文章
@Lonely__MH: 晚上体验了下 Reasonix,被种草了 绝对是 DeepSeek 最佳伴侣! 颜值在线,还能实时查看 DeepSeek 账户余额。 看文档介绍,它作为原生后端终端编程 Agent,主打的就是 Cache-First 循环和 Flash …
Reasonix 是一个专为 DeepSeek 设计的原生后端终端编程 Agent,采用 Cache-First 循环和 Flash 优化策略,能够显著降低 API 调用成本并实时查看账户余额,是 DeepSeek 生态中的实用伴侣工具。
@QingQ77: 一个专为 DeepSeek API 前缀缓存机制设计的终端 AI 编程代理,通过缓存优先的架构在长会话中保持超低 token 成本。 https://github.com/esengine/DeepSeek-Reasonix… Reaso…
Reasonix 是一个专为 DeepSeek API 前缀缓存机制设计的终端 AI 编程代理,通过缓存优先架构在长会话中实现超低 token 成本。实测 4.35 亿输入 token 仅花费约 12 美元,缓存命中率 99.82%。
@wsl8297: 平时拿 DeepSeek 写代码的人,可以看看 DeepSeek-Code-Whale。 GitHub:https://github.com/usewhale/DeepSeek-Code-Whale… 开源终端 AI 编程 Agent,专…
DeepSeek-Code-Whale 是一个开源的终端 AI 编程代理,专门为 DeepSeek 模型优化,支持 MCP 工具、Skills 扩展、前缀缓存优化(90% 缓存命中率)和 1M 上下文窗口,旨在降低 AI 编程成本并提供高效的命令行工作流。
DeepSeek reasonix,DeepSeek 原生编码代理,高缓存、低成本
DeepSeek 发布了一款名为 DeepSeek reasonix 的原生编码代理,具有高缓存和低成本特点。
@GithubProjects: Reasonix 是一款专为 DeepSeek 设计的终端 AI 编程代理,旨在通过稳定前缀缓存降低 token 成本……
Reasonix 是一款针对 DeepSeek 模型优化的终端 AI 编程代理,通过稳定前缀缓存实现了 99.82% 的缓存命中率,并将每次工作负载的 token 成本从约 61 美元降至约 12 美元。