Self-built ReAct agent loop engine with
reasoning_contentfull round-trip caching, directly connecting to the DeepSeek V4 API — $0.14/M tokens, 1M context, thinking mode fully managed.
首个将reasoning_contentround-trip 回传作为核心设计的 agent loop 引擎——$0.14/M tokens 起，1M context，thinking 模式全托管。
loop-deepseek is an alternative to LangChain / AutoGPT / CrewAI agent frameworks, specifically optimized for DeepSeek V4's reasoning_content round-trip caching. It uses a zero-dependency, self-built ReAct loop compiled to a single Bun binary.
- Self-built ReAct loop — Thought → Action → Observation → Thought cycle, zero framework dependencies.
reasoning_contentround-trip caching — the only agent engine that preservesreasoning_contentacross turns, avoiding redundant reasoning costs.- Three reasoning strategies —
FULL_RETENTION(primary),CACHE_INJECTION(compaction recovery),THINKING_DISABLED(fallback). - 6 built-in tools —
bash(sandboxed),read,write,edit,glob,grep— no MCP or external tool servers needed. - Guard layer — pure-function
banned_behaviorsengine with L0 / L1 / L2 severity levels, compiled into the binary, bypass-proof. - Token budget tracker — separate reasoning / completion / prompt token counters; 90% compaction threshold, 98% hard stop.
- Cost control —
--budget-limithard cap with real-time estimation and reasoning cache hit-rate statistics.
# Clone and install
git clone https://github.com/PerryLink/loop-deepseek.git
cd loop-deepseek
bun install
bun run src/index.ts
# Or build a standalone binary
bun build --compile --target=bun src/index.ts --outfile loop-deepseek
# Run with a goal and budget
./loop-deepseek --goal "Build a Python CLI weather tool" --budget-limit 5.00
# Set your API key
export DEEPSEEK_API_KEY="sk-..."Requirements: Bun >= 1.0.0, DeepSeek API key (platform.deepseek.com).
Q: What makes reasoning_content round-trip special?
Every other agent framework discards the model's internal reasoning after each tool call — the next turn starts with a blank reasoning slate. This forces the model to re-reason from scratch, wasting tokens. DeepSeek V4 exposes reasoning_content in its API response. loop-deepseek is the first agent engine to cache and re-inject it, so the model picks up where it left off — slashing reasoning token costs by 40–60 % on multi-turn tasks.
Q: Can I use this with OpenAI-compatible endpoints?
Yes. loop-deepseek supports both the native DeepSeek API endpoint (primary, for reasoning_content access) and an OpenAI-compatible fallback endpoint. Set --endpoint openai-compat to use compatibility mode. Note that reasoning_content is only available on the native endpoint.
Q: What happens when I hit the budget limit?
The loop stops gracefully at the next tool-call boundary. It logs the current state, partial artifacts, and a cost summary to state.json. You can increase the budget and resume with --state-file state.json.
Q: How do I run tests?
bun test # run all tests
bun test --coverage # with coverage report
bun run lint # ESLint check
bun run format:check # Prettier checkloop-deepseek 是 LangChain / AutoGPT / CrewAI agent 框架的替代方案，专为 DeepSeek V4 的 reasoning_content round-trip 缓存优化。零依赖、自建 ReAct 循环，编译为单个 Bun 二进制文件。
- 🔄 自建 ReAct 循环 — Thought → Action → Observation → Thought 循环，零框架依赖。
- 🧠
reasoning_contentround-trip 缓存 — 唯一跨轮保留reasoning_content的 agent 引擎，避免重复推理成本。 - 🎯 三种推理策略 —
FULL_RETENTION（主策略）、CACHE_INJECTION（压缩恢复）、THINKING_DISABLED（回退）。 - 🛠️ 6 个内置工具 —
bash（沙箱）、read、write、edit、glob、grep— 无需 MCP 或外部工具服务器。 - 🛡️ Guard 层 — 纯函数
banned_behaviors引擎，L0 / L1 / L2 三级拦截，编译进二进制，不可绕过。 - 💰 Token 预算追踪 — 独立的 reasoning / completion / prompt token 计数器；90% 压缩阈值，98% 硬停止。
- 💵 成本控制 —
--budget-limit硬上限，带实时估算和 reasoning 缓存命中率统计。
# 克隆并安装
git clone https://github.com/PerryLink/loop-deepseek.git
cd loop-deepseek
bun install
bun run src/index.ts
# 或编译独立二进制文件
bun build --compile --target=bun src/index.ts --outfile loop-deepseek
# 带目标和预算运行
./loop-deepseek --goal "用 Python 构建 CLI 天气工具" --budget-limit 5.00
# 设置 API 密钥
export DEEPSEEK_API_KEY="sk-..."环境要求： Bun >= 1.0.0，DeepSeek API 密钥（platform.deepseek.com）。
Q: reasoning_content round-trip 有什么特别之处？
所有其他 agent 框架在每次工具调用后都会丢弃模型的内部推理——下一轮从空白的推理状态开始。这迫使模型从头重新推理，浪费了大量 token。DeepSeek V4 在其 API 响应中暴露了 reasoning_content。loop-deepseek 是首个将其缓存并重新注入的 agent 引擎，让模型从上次中断处继续——在多轮任务中可节省 40–60% 的推理 token 成本。
Q: 能否用于 OpenAI 兼容端点？
可以。loop-deepseek 同时支持原生 DeepSeek API 端点（主模式，用于访问 reasoning_content）和 OpenAI 兼容回退端点。使用 --endpoint openai-compat 启用兼容模式。注意：reasoning_content 仅在原生端点上可用。
Q: 达到预算上限会发生什么？
循环会在下一个工具调用边界优雅停止，将当前状态、部分产物和成本摘要记录到 state.json。您可以增加预算，然后通过 --state-file state.json 恢复运行。
Q: 如何运行测试？
bun test # 运行所有测试
bun test --coverage # 带覆盖率报告
bun run lint # ESLint 检查
bun run format:check # Prettier 检查| Project | Description / 描述 |
|---|---|
| loop-superpowers | Pure Skill mini-loops for Claude Code / Claude Code 纯 Skill 迷你循环 |
| loop-opencode | Closed-loop driver for OpenCode CLI / OpenCode CLI 闭环驱动 |
| loop-codex | Dual-channel (JSON-RPC + CDP) driver for Codex Desktop / Codex Desktop 双通道驱动 |
| loop-copilot | Closed-loop driver for GitHub Copilot SDK / GitHub Copilot SDK 闭环驱动 |
| loop-cursor | Closed-loop driver for Cursor IDE SDK / Cursor IDE SDK 闭环驱动 |
| loop-ollama | Self-built ReAct agent loop for local Ollama models / 本地 Ollama 模型自建 ReAct 循环 |
| loop-antigravity | Closed-loop driver for Google Antigravity / Gemini / Google Antigravity / Gemini 闭环驱动 |
| loop-openclaw | Multi-agent loop config generator for OpenClaw Gateway / OpenClaw Gateway 多 agent 循环配置生成器 |
Apache License 2.0 — see LICENSE for full text.
Copyright 2026 Perry Link