Coding & Development๐คclaude๐universal
ClawCodex
Token efficient Claude Code full Python rebuild. AI Coding Agent in 270K LoC pure Python. Up to 200X Cost Saving!
Quick Start
Install this Skill
npx skills add agentforce314/clawcodex<div align="center">
**English** | [ไธญๆ](docs/i18n/README_ZH.md) | [Franรงais](docs/i18n/README_FR.md) | [ะ ัััะบะธะน](docs/i18n/README_RU.md) | [เคนเคฟเคจเฅเคฆเฅ](docs/i18n/README_HI.md) | [ุงูุนุฑุจูุฉ](docs/i18n/README_AR.md) | [Portuguรชs](docs/i18n/README_PT.md)
# ClawCodex
**A production-oriented Python rebuild of Claude Code โ real architecture, reliable CLI agent**
*Ported from the TypeScript reference implementation and extended with a Python-native runtime*
***
[](https://github.com/agentforce314/clawcodex/stargazers)
[](https://github.com/agentforce314/clawcodex/network/members)
[](https://opensource.org/licenses/MIT)
[](https://www.python.org/downloads/)
**๐ฅ Active Development โข New Features Weekly ๐ฅ**

</div>
***
<div align="center">
# ๐ฟโ๏ธ /eco Token Compression
# Same session, **80% fewer** Bash-output tokens
### Measured, not estimated: 27 real command outputs replayed through the production pipeline โ **92,989 โ 17,767 tokens (-80%)**. Failure summaries keep the error lines that matter; anything lossy is teed to disk, one `tail` away.
One toggle, deterministic filters โ failure-focused test summaries, `git`/`pip`/`npm` ceremony
stripping, log dedup, recoverable head-caps โ guarded to be **never worse** than the raw rendering.
Stacks with the [DeepSeek prefix cache](#-deepseek-prefix-cache): the cache makes your stable
prefix nearly free, `/eco` shrinks the fresh suffix every turn actually pays for.
**[See the measured benchmark โ](#eco-benchmark)**
</div>
***
<div align="center">
# ๐๐ฅ DeepSeek Prefix Cache
# Run long agentic coding sessions for *pennies*
### Cache-hit input bills at **`~$0.0435` / 1M tokens** โ about **230ร cheaper** than Claude Fable 5 (`$10` / 1M).
ClawCodex keeps your request prefix **byte-stable**, so DeepSeek's prompt cache covers your whole
`system + tools + history` span across turns. **The longer you code, the more you save.**
</div>
***
## โก Quick Install
**One line** โ installs `uv`, Python 3.10+, and puts `clawcodex` on your PATH:
```bash
curl -fsSL https://clawcodex.app/install.sh | bash
```
Then configure a provider and start coding:
```bash
clawcodex login # interactive provider + API key setup โ ~/.clawcodex/config.json
clawcodex --dangerously-skip-permissions # start the REPL in any project
```
The installer also ships `clawcodex` lifecycle helpers โ `doctor` (diagnose your
environment), `verify` (health-check the install), `update`, and `uninstall`. It is
re-run-safe and works on macOS, Linux, and WSL. To pass flags through the pipe, use
`curl -fsSL https://clawcodex.app/install.sh | bash -s -- --dry-run`.
<details>
<summary><b>Or install manually from source</b></summary>
```bash
git clone https://github.com/agentforce314/clawcodex.git
cd clawcodex
python3 -m venv .venv && source .venv/bin/activate # Python 3.10+
pip install -r requirements.txt
python -m src.cli login # writes config to ~/.clawcodex/config.json
python -m src.cli --dangerously-skip-permissions # start the REPL
```
</details>
The configuration file is saved at `~/.clawcodex/config.json`. Minimal example:
```json
{
"default_provider": "deepseek",
"providers": {
"deepseek": {
"api_key": "xxx-xxx",
"base_url": "https://api.deepseek.com",
"default_model": "deepseek-v4-pro"
}
},
"env": {
"TAVILY_API_KEY": "tvly-YOUR-TAVILY-API-KEY"
}
}
```
> **Note:** `TAVILY_API_KEY` is required for the WebSearch tool โ get a key at [tavily.com](https://tavily.com).
The `session`, `settings`, and `env` blocks are optional โ sensible defaults apply when they're omitted. See [Configure](#configure) for the full structure.
***
## ๐ฐ News
- **2026-07-13:** **`/eco` token compression โ -80% Bash-output tokens, measured, now a headline (#708, #712)** โ a new session toggle compresses the model-bound rendering of every Bash result with deterministic filters ported from [RTK](https://github.com/rtk-ai/rtk)'s method set: failure-focused test summaries (kept error lines are never rewritten), `git`/`pip`/`npm` ceremony stripping, log dedup with `[รN]` counts, and a recoverable head-cap โ all behind a **never-worse** guard, with every lossy compression teeing the full output to disk behind a runnable recovery hint (#708). A reproducible benchmark (`eval/eco/`) replays 27 real command outputs through the exact production pipeline and counts real tokenizer tokens: **92,989 โ 17,767 (-80%)** corpus-wide, -88% on filter hits, plus an honestly conservative r
... (truncated)Repository
812stars
145forks
Details
Related Skills
More coding & development skills you might like
Reticle
Coding & DevelopmentAI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.
๐คclaude๐universal
1.2k
190
View
agentscope-java
Coding & DevelopmentExpert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or Java agent development. Specializes in non-blocking code, tool integration, hooks, pipelines, and production-ready agent applications.
๐universal
6.0k
1.5k
View
ospec
Coding & DevelopmentDocument-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
โจgemini๐คclaude๐ฌgpt๐universal
524
34
View
misakanet-failure-memory
Coding & Development๐ A zero-dependency, git-backed micro-lesson library for AI Agents to asynchronously share and search verified debugging experience. Python stdlib only. | https://misakanet.org
๐คclaudeโจ๏ธcursor๐universal
424
158
View