Clawcode

<p align="center"> <img width="256" height="256" alt="Screenshot - 2026-03-26 20 36 43" src="https://github.com/user-attachments/assets/03466089-8b3d-47f8-a454-06a8874eb727" /> </p> <h1 align="center">ClawCode</h1> <p align="center"> <strong>Your creative dev tool , AI coding Swiss Army knife</strong> </p> <p align="center"> <a href="https://github.com/deepelementlab/clawcode/releases"> <img src="https://img.shields.io/static/v1?style=flat&label=release&labelColor=6A737D&color=fe7d37&message=v0.1.1" alt="Release v0.1.1" /> </a> <a href="#license"><img src="https://img.shields.io/badge/license-GPL%20OR%20Apache%202.0-blue.svg" alt="License: GPL-3.0" /></a> <a href="https://github.com/deepelementlab/clawcode/wiki"><img src="https://img.shields.io/badge/Wiki-documentation-26A5E4?style=flat&logo=github&logoColor=white"alt="Documentation Wiki"/></a> <a href="https://gitcgr.com/deepelementlab/clawcode"> <img src="https://gitcgr.com/badge/nearai/clawcode.svg" alt="gitcgr" /> </a> </p> <p align="center"> <a href="README.md">English</a> | <a href="README.zh.md">简体中文</a> </p> <p align="center"> <a href="#philosophy">Philosophy</a> • <a href="#product-vision">Product vision</a> • <a href="#development-assistance-functions">Development assistance functions</a> • <a href="#system-architecture">System Architecture</a> • <a href="#value-at-a-glance">Value at a glance</a> • <a href="#get-started">Get started</a> </p>

ClawCode is a Claude Code‑inspired implementation in Python and Rust, focused on agents and experience‑based evolution. It is also an open‑source coding‑agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimi, Ollama, Codex, GitHub Models, and 200+ models via OpenAI‑compatible APIs.

<img width="2549" height="930" alt="ClawCode screenshot" src="https://github.com/user-attachments/assets/6cc0814a-aa3e-4f56-98dc-5123ecf88a1c" />

Philosophy

We aim to build an open, excellent AI coding Swiss Army knife.

It starts with a coder agent framework (tool use, skills, memory, multi‑agent). On this we built Claw, adding more tools, OpenClaw skill compatibility, and computer‑use abilities.

But that's not enough. Our own projects generate valuable development data through iterations. We shouldn't waste them.

So we built a self‑improving subsystem: it uses that data to continuously enhance the agents. All data stays local, under your control. The system is open source, auditable, with no hidden telemetry.

In short: an experience‑based reinforcement learning framework that turns

Idea → Memory → Plan → Code → Verify → Review → Learned Experience

into an executable, learnable, evolving engineering loop.

---

Product vision

ClawCode is a creative dev tool aimed at real delivery.

Features:

<img width="1376" height="768" alt="Generated_image" src="https://github.com/user-attachments/assets/1a09bd15-9859-413d-a1f3-f0c573e12b99" />

Core motivations:

• Turn ideas into runnable code quickly
  From “I have an idea” to “implemented and verified,” with less context switching and tool friction.

• Stay vendor- and model-agnostic
  Configurable providers/models and open extension paths reduce lock-in.

• Reuse strong UX patterns instead of reinventing habits
  Learn from mature tools (e.g. Claude Code, Cursor) and preserve familiar workflows where possible.

• Remember usage and improve over time
  Session persistence, experience write-back, and closed-loop learning let the system evolve with tasks and team practice.

• Execute “full-stack” engineering tasks end-to-end
  Beyond one-off codegen: planning, delegation, execution, verification, review, and structured learning.

Development assistance functions

Architecture & review

| Command | Function | |--------|----------| | /architect | Run architecture design/review workflow with trade-off analysis and ADR/checklist options. | | /code-review | Review local uncommitted changes with severity-ranked findings and commit gate. | | /security-review | Complete a security review of the pending changes on the current branch. | | /review | Review a pull request. |

Autocomplete / related planning & plugins

| Command | Function | |--------|----------| | /plan | Enable plan mode or view the current session plan (handled in ChatScreen; listed for autocomplete). | | /arc-plan | Generate a one-shot alternative implementation plan (ARC planner). | | /plugin | Manage clawcode plugins. |

Test-driven development

| Command | Function | |--------|----------| | /tdd | Run strict TDD workflow: scaffold, RED, GREEN, refactor, and coverage gate. |

Multi-role orchestration & engineering workflows

| Command | Function | |--------|----------| | /clawteam | Run multi-role task orchestration, or target one role via /clawteam:<agent>. Supports --deep_loop for iterative convergence (see docs/CLAWTEAM_SLASH_GUIDE.md). | | /clawteam-deeploop-finalize | Parse DEEP_LOOP_WRITEBACK_JSON from pasted or last assistant text using pending deep-loop session metadata. | | /multi-plan | Run multi-model collaborative planning workflow (plan-only). | | /multi-execute | Run multi-model collaborative execution workflow with traceable artifacts. | | /multi-backend | Run backend-focused multi-model workflow (research through review, orchestrator writes code). | | /multi-frontend | Run frontend-focused multi-model workflow (UI/UX led, orchestrator writes code). | | /multi-workflow | Run full-stack multi-model workflow (backend + UI advisors, orchestrator writes code). | | /orchestrate | Run sequential multi-role workflow (HANDOFF between planner/TDD/review/security/architect); /orchestrate show\|list. |

Learning loop: ECAP, TECAP & instincts

| Command | Function | |--------|----------| | /learn | Learn reusable instincts from recent tool observations. | | /learn-orchestrate | Run observe → evolve → import-to-skill-store orchestration in one command. | | /experience-create | Create an ECAP experience capsule from recent observations/instincts. | | /experience-status | List available ECAP capsules with optional filters. | | /experience-export | Export an ECAP capsule as JSON/Markdown for model or human use. | | /experience-import | Import an ECAP capsule from local file or URL. | | /experience-apply | Apply an ECAP capsule as one-shot agent prompt context. | | /experience-feedback | Record success/failure feedback score for an ECAP capsule. | | /team-experience-create | Create a TECAP team-experience capsule from collaborative traces. | | /team-experience-status | List TECAP capsules with optional team/problem filters. | | /team-experience-export | Export a TECAP capsule as JSON/Markdown for agents and humans. | | /team-experience-import | Import a TECAP capsule from local file or URL. | | /team-experience-apply | Apply a TECAP capsule as collaboration context prompt. | | /team-experience-feedback | Record feedback score for a TECAP capsule. | | /tecap-create | Alias of /team-experience-create. | | /tecap-status | Alias of /team-experience-status. | | /tecap-export | Alias of /team-experience-export. | | /tecap-import | Alias of /team-experience-import. | | /tecap-apply | Alias of /team-experience-apply. | | /tecap-feedback | Alias of /team-experience-feedback. | | /instinct-status | Show learned instincts grouped by domain and confidence. | | /instinct-import | Import instincts from local file or URL into inherited set. | | /instinct-export | Export instincts with optional domain/confidence filters. | | /evolve | Cluster instincts and optionally generate evolved structures. | | /experience-dashboard | Show ECAP-first experience metrics dashboard (add --json or --no-alerts). | | /closed-loop-contract | Show closed-loop config contract coverage (consumed vs unconsumed keys). |

Observability, diagnostics & diffs

| Command | Function | |--------|----------| | /doctor | Diagnose and verify your clawcode installation and settings. | | /diff | View uncommitted changes and per-turn diffs. | | /debug | Debug your current clawcode session via logs (bundled viewer). | | /insights | Generate a report analyzing your clawcode sessions. |

Claw mode & external CLIs

| Command | Function | |--------|----------| | /claw | Enable Claw agent mode or show status (autocomplete entry; see SLASH_AUTOCOMPLETE_EXTRA in builtin_slash.py). | | /claude | Enable Claw mode then path A: Anthropic + Claude Code HTTP identity. | | /claude-cli | Enable Claw mode then path B: run claude / claude-code CLI in workspace. | | /opencode-cli | Enable Claw mode then path B′: run OpenCode opencode CLI in workspace. | | /codex-cli | Enable Claw mode then path B″: run OpenAI Codex CLI in workspace. |

Session, Git, workspace & engineering context

| Command | Function | |--------|----------| | /checkpoint | Git workflow checkpoints: create, verify, list, clear. | | /rewind | Soft-archive chat after a message, or inspect/restore tracked git files. | | /tasks | List and manage background tasks (plan build, agent run). | | /init | Initialize CLAWCODE.md (or CLAW.md-style) codebase documentation in the project. | | /add-dir | Add a new working directory. | | /agents | Manage agent configurations. | | /skills | List available skills. | | /mcp | Manage MCP servers. | | /hooks | Manage hook configurations for tool events. | | /permissions | Manage allow & deny tool permission rules. | | /memory | Edit claw memory files. | | /pr-comments | Get comments from a GitHub pull request. |

System Architecture

<img width="1376" height="768" alt="Generated_image_architecture" src="https://github.com/user-attachments/assets/1bd96e39-8ca3-4e96-8698-dbc755ce94ab" />

Compatible with Claude Code (config & plugins & skills)

To lower learning and migration cost, ClawCode