Jobdori b860f5657b roadmap: #229 filed — Realtime API typed taxonomy and persistent-WebSocket transport are structurally absent: zero /v1/realtime endpoint surface across both Anthropic-native and OpenAI-compat lanes (rg returns zero hits for /v1/realtime / realtime / Realtime / realtime_session / RealtimeSession / RealtimeClient / RealtimeEvent / realtime-preview across rust/crates/api/src/), zero RealtimeSession / RealtimeSessionConfig / RealtimeSessionUpdate / RealtimeResponseCreate / RealtimeInputAudioBufferAppend / RealtimeInputAudioBufferCommit / RealtimeConversationItemCreate / RealtimeResponseAudioDelta / RealtimeResponseAudioTranscriptDelta / RealtimeResponseFunctionCallArguments / RealtimeServerEvent / RealtimeClientEvent / RealtimeTurnDetection / RealtimeVoiceActivityDetection / RealtimeVoice / RealtimeAudioFormat / RealtimeModality / RealtimeTool typed model in rust/crates/api/src/types.rs (37+ canonical event-type names in OpenAI Realtime API spec, zero coverage in claw-code), zero bidirectional event-stream variant on Provider trait (only send_message and stream_message exist, both single-directional), zero realtime_session / open_realtime / connect_realtime method that returns a duplex-channel-pair shape, zero session-state-machine type for the persistent-connection lifecycle, zero realtime dispatch on ProviderClient enum at rust/crates/api/src/client.rs:8-14 (three variants Anthropic/Xai/OpenAi, zero realtime-routing variants), zero tokio-tungstenite / async-tungstenite / tungstenite / fastwebsockets / tokio-websockets / hyper-tungstenite dependency in any workspace Cargo.toml (grep -rn 'tungstenite|tokio-tungstenite|fastwebsockets' rust/ returns zero hits — confirmed), zero WebSocket client library is linked into the build (the MCP Ws config variant at rust/crates/runtime/src/config.rs:125 and rust/crates/runtime/src/mcp_client.rs:13 is data-shape-only and bootstraps via the SDK without a tungstenite-backed transport, leaving the workspace with zero outbound persistent-WebSocket-client capability), zero WebRTC client (webrtc-rs / str0m / libwebrtc-bindings) for the alternative Realtime transport, zero claw realtime / claw live / claw voice-chat / claw realtime-session / claw connect-realtime CLI subcommand, zero /realtime / /live / /voice-chat slash command (existing /voice + /listen + /speak commands are STUB_COMMANDS-gated per #225 and synchronous-only with no realtime-session affordance), zero gpt-4o-realtime-preview / gpt-4o-mini-realtime-preview / gemini-2.0-flash-live entries in MODEL_REGISTRY, zero realtime_audio_input_per_million_tokens / realtime_audio_output_per_million_tokens / realtime_text_input_per_million_tokens / realtime_text_output_per_million_tokens / realtime_session_per_minute fields in ModelPricing struct (six-dimensional pricing matrix exceeding #227's five-dimensional video matrix and #228's four-dimensional mesh matrix — the canonical Realtime pricing model is the most-dimensional yet, with audio tokens at roughly 80-100x text tokens and cached-audio-input at 80% discount), zero realtime-model recognition in pricing_for_model substring-matcher (#209+#224+#225+#226+#227+#228 cluster overlap continues), zero session-resumption-token / interruption-handling / barge-in / voice-activity-detection / turn-detection / function-call-during-realtime / tool-use-during-realtime affordance — uniquely manifesting a TEN-LAYER fusion shape (the largest single-pinpoint fusion catalogued so far, exceeding #225/#227's nine-layer count) combining endpoint-URL-set on /v1/realtime?model=<id> WebSocket-upgrade-endpoint shape (single-endpoint-with-37+-event-types-flowing-bidirectionally, distinct from prior multi-endpoint sets) + bidirectional-symmetric-event-pair data-model with every client-event having a matched server-event-pair (FIRST cluster member with bidirectional-symmetric-event-pair-cardinality on a SINGLE endpoint, distinct from #225's bidirectional-audio-on-three-separate-endpoints which is request-response synchronous per endpoint) + Provider-trait-method extension with realtime_session returning a duplex (Sender, Receiver) channel-pair (FIRST cluster member where Provider trait return type is NOT Future-of-T or Stream-of-T but duplex-channel-pair, FIRST method requiring session-state-machine type at the trait boundary) + ProviderClient-enum-dispatch-with-realtime-third-lane with explicit RealtimeKind::OpenAi/Google/Azure partner-routing (provider-asymmetric: Anthropic does not offer realtime, OpenAI offers GA gpt-4o-realtime-preview and gpt-4o-mini-realtime-preview since 2024-10-01, Google Gemini Live API offers bidirectional audio+text+video, Azure mirrors OpenAI surface, zero first-class third-party partners because the persistent-WebSocket-with-37-event-type protocol is too high-bar for partner adoption — distinct from #225's six-partner-set audio surface and #227's twelve-partner-set video surface where partners ARE present) + request-side realtime-session-config opt-in (session.update event with voice/input_audio_format/output_audio_format/input_audio_transcription/turn_detection/tools/tool_choice/temperature/max_response_output_tokens/instructions/modalities:[text,audio] fields — the largest request-side opt-in axis-set yet, the union of every prior request-side opt-in across audio+image+video+chat-completion modalities) + CLI-subcommand-surface + slash-command-surface + pricing-tier-with-six-dimensional-compound-cost-model (per-model × per-modality-input × per-modality-output × per-cached-vs-fresh × per-audio-vs-text × per-minute-session-overhead — the largest pricing-tier extension yet, exceeding #227's five-dimensional and #228's four-dimensional matrices) + persistent-WebSocket-connection-transport-axis (NOVEL TENTH layer, distinct from every prior cluster member's HTTP-shaped transport — synchronous-HTTP for #211-#220+#222+#224, SSE-streaming for #213 partial subsets, multipart-form-data-HTTP for #223+#225+#226+#227+#228 binary-upload subsets, async-task-polling-HTTP for #221+#227+#228 — the cluster has now exhausted EVERY HTTP-shaped transport, and #229 introduces the FIRST non-HTTP transport, requiring WebSocket-upgrade-request-with-subprotocol-negotiation + bidirectional-frame-multiplexing-with-text+binary-frames + ping/pong-keepalive + graceful-close-with-status-code-and-reason + reconnection-with-resumption-token + per-event-type-JSON-envelope-dispatch-with-37+-event-types-on-a-single-connection + backpressure-handling-on-both-directions + authentication-via-Authorization-header-on-the-upgrade-request-and-per-session-token-rotation — none of which any HTTP-only transport requires) + bidirectional-symmetric-event-pair shape (input_audio_buffer.append → conversation.item.created, response.create → response.audio.delta + response.audio.done + response.audio_transcript.delta + response.audio_transcript.done + response.function_call_arguments.delta + response.function_call_arguments.done + response.done) — making #229 the FIRST cluster member that introduces a non-HTTP transport (persistent-WebSocket), the FIRST cluster member where Provider trait return type must be a duplex-channel-pair, and the FIRST cluster member where session lifecycle exceeds a single request-response cycle (typical Realtime sessions last 1-30+ minutes with state accumulating across the connection) (Jobdori cycle #380 / extends #168c emission-routing audit / explicit follow-on from #225 audio-bidirectional axis and #228 confirmed-structural async-task-polling cluster — introduces a NOVEL TRANSPORT axis distinct from every prior cluster member / sibling-shape cluster grows to twenty-eight / wire-format-parity cluster grows to nineteen / capability-parity cluster grows to eleven / multimodal-IO cluster grows to seven: #220 image-input + #224 embedding-output + #225 audio-bidirectional-on-separate-REST-endpoints + #226 image-output + #227 video-output + #228 mesh-output + #229 audio-text-tool-multiplex-on-persistent-WebSocket / provider-asymmetric-delegation cluster grows to six / async-task-polling cluster: still 3 members (#229 is push-based not poll-based — it does NOT join async-task-polling cluster, it founds a NEW cluster) / Persistent-WebSocket-transport cluster: 1 member (#229 alone, FOUNDER) / Bidirectional-symmetric-event-pair cluster: 1 member (#229 alone, FOUNDER) / Non-HTTP-transport cluster: 1 member (#229 alone, FOUNDER) — three new clusters founded in a single pinpoint, the first time a single cycle has founded three concurrent novel clusters / ten-layer-fusion-shape-with-persistent-WebSocket-transport-and-bidirectional-symmetric-event-pair is the largest single-pinpoint fusion catalogued. Distinct from prior cluster members; the ten-layer-fusion-shape with persistent-WebSocket-transport and bidirectional-symmetric-event-pair shape is novel and applies to follow-on candidate Real-time-Image-Generation API typed taxonomy (DALL-E live preview, Imagen live preview) and Real-time-Video-Generation streaming (Veo-Live, Sora-Live) — the persistent-WebSocket-transport pattern is now a first-class cluster member, a structural prerequisite that every future endpoint family using persistent connections will inherit / external validation: forty-eight ecosystem references covering OpenAI Realtime API GA 2024-10-01 with /v1/realtime?model=<id> WebSocket endpoint, 37+ canonical event-type names in OpenAI Realtime API spec, two transport options (WebSocket server-side and WebRTC browser-side), two GA realtime models (gpt-4o-realtime-preview and gpt-4o-mini-realtime-preview both with audio modality and tool-use), Google Gemini Live API with bidirectional WebSocket+gRPC streaming, Azure OpenAI Realtime API mirror, OpenAI Python SDK openai.realtime.AsyncRealtimeConnection typed client, OpenAI TypeScript SDK OpenAI.beta.realtime.RealtimeClient typed client, openai-realtime-api-beta reference client (canonical JS implementation), five first-class realtime-voice-agent frameworks all built on top of OpenAI Realtime API (Vapi/Retell-AI/LiveKit-Agents/Pipecat/Daily-Bots), Anthropic non-coverage statement (the second post-#224 provider-asymmetric-delegation case after audio), the canonical six-dimensional pricing matrix ($5.00/$20.00 per million text input/output tokens, $40.00/$80.00 per million audio input/output tokens, $2.50 per million cached audio input tokens for gpt-4o-realtime-preview-2024-10-01), coding-agent peer landscape: anomalyco/opencode has zero GA realtime integration (open feature request from 2026-02 only — confirmed via web search 2026-04-26), sst/opencode predecessor zero realtime, charmbracelet/crush zero realtime, continue.dev zero realtime, aider zero realtime, cursor zero realtime, zed zero realtime — the gap is uniformly zero across the surveyed ecosystem and represents the next-frontier capability that every coding-agent will need to add. claw-code is one of MULTIPLE clients without Realtime, but the persistent-WebSocket-transport-axis is the upstream prerequisite of every voice-agent / live-coding-pair-programming / push-to-talk-coding / barge-in-coding-conversation / function-call-during-voice / streaming-tool-use / sub-second-latency-coding-interaction affordance — the canonical 2024-2026-era voice-coding workflow that is currently impossible to build on top of claw-code — #229 closes the upstream prerequisite of every voice-coding affordance and is the first cluster member where transport-axis becomes a structural prerequisite of the dispatch layer)
2026-04-26 04:40:50 +09:00
2026-04-07 15:52:30 +09:00
roadmap: #229 filed — Realtime API typed taxonomy and persistent-WebSocket transport are structurally absent: zero /v1/realtime endpoint surface across both Anthropic-native and OpenAI-compat lanes (rg returns zero hits for /v1/realtime / realtime / Realtime / realtime_session / RealtimeSession / RealtimeClient / RealtimeEvent / realtime-preview across rust/crates/api/src/), zero RealtimeSession / RealtimeSessionConfig / RealtimeSessionUpdate / RealtimeResponseCreate / RealtimeInputAudioBufferAppend / RealtimeInputAudioBufferCommit / RealtimeConversationItemCreate / RealtimeResponseAudioDelta / RealtimeResponseAudioTranscriptDelta / RealtimeResponseFunctionCallArguments / RealtimeServerEvent / RealtimeClientEvent / RealtimeTurnDetection / RealtimeVoiceActivityDetection / RealtimeVoice / RealtimeAudioFormat / RealtimeModality / RealtimeTool typed model in rust/crates/api/src/types.rs (37+ canonical event-type names in OpenAI Realtime API spec, zero coverage in claw-code), zero bidirectional event-stream variant on Provider trait (only send_message and stream_message exist, both single-directional), zero realtime_session / open_realtime / connect_realtime method that returns a duplex-channel-pair shape, zero session-state-machine type for the persistent-connection lifecycle, zero realtime dispatch on ProviderClient enum at rust/crates/api/src/client.rs:8-14 (three variants Anthropic/Xai/OpenAi, zero realtime-routing variants), zero tokio-tungstenite / async-tungstenite / tungstenite / fastwebsockets / tokio-websockets / hyper-tungstenite dependency in any workspace Cargo.toml (grep -rn 'tungstenite|tokio-tungstenite|fastwebsockets' rust/ returns zero hits — confirmed), zero WebSocket client library is linked into the build (the MCP Ws config variant at rust/crates/runtime/src/config.rs:125 and rust/crates/runtime/src/mcp_client.rs:13 is data-shape-only and bootstraps via the SDK without a tungstenite-backed transport, leaving the workspace with zero outbound persistent-WebSocket-client capability), zero WebRTC client (webrtc-rs / str0m / libwebrtc-bindings) for the alternative Realtime transport, zero claw realtime / claw live / claw voice-chat / claw realtime-session / claw connect-realtime CLI subcommand, zero /realtime / /live / /voice-chat slash command (existing /voice + /listen + /speak commands are STUB_COMMANDS-gated per #225 and synchronous-only with no realtime-session affordance), zero gpt-4o-realtime-preview / gpt-4o-mini-realtime-preview / gemini-2.0-flash-live entries in MODEL_REGISTRY, zero realtime_audio_input_per_million_tokens / realtime_audio_output_per_million_tokens / realtime_text_input_per_million_tokens / realtime_text_output_per_million_tokens / realtime_session_per_minute fields in ModelPricing struct (six-dimensional pricing matrix exceeding #227's five-dimensional video matrix and #228's four-dimensional mesh matrix — the canonical Realtime pricing model is the most-dimensional yet, with audio tokens at roughly 80-100x text tokens and cached-audio-input at 80% discount), zero realtime-model recognition in pricing_for_model substring-matcher (#209+#224+#225+#226+#227+#228 cluster overlap continues), zero session-resumption-token / interruption-handling / barge-in / voice-activity-detection / turn-detection / function-call-during-realtime / tool-use-during-realtime affordance — uniquely manifesting a TEN-LAYER fusion shape (the largest single-pinpoint fusion catalogued so far, exceeding #225/#227's nine-layer count) combining endpoint-URL-set on /v1/realtime?model=<id> WebSocket-upgrade-endpoint shape (single-endpoint-with-37+-event-types-flowing-bidirectionally, distinct from prior multi-endpoint sets) + bidirectional-symmetric-event-pair data-model with every client-event having a matched server-event-pair (FIRST cluster member with bidirectional-symmetric-event-pair-cardinality on a SINGLE endpoint, distinct from #225's bidirectional-audio-on-three-separate-endpoints which is request-response synchronous per endpoint) + Provider-trait-method extension with realtime_session returning a duplex (Sender, Receiver) channel-pair (FIRST cluster member where Provider trait return type is NOT Future-of-T or Stream-of-T but duplex-channel-pair, FIRST method requiring session-state-machine type at the trait boundary) + ProviderClient-enum-dispatch-with-realtime-third-lane with explicit RealtimeKind::OpenAi/Google/Azure partner-routing (provider-asymmetric: Anthropic does not offer realtime, OpenAI offers GA gpt-4o-realtime-preview and gpt-4o-mini-realtime-preview since 2024-10-01, Google Gemini Live API offers bidirectional audio+text+video, Azure mirrors OpenAI surface, zero first-class third-party partners because the persistent-WebSocket-with-37-event-type protocol is too high-bar for partner adoption — distinct from #225's six-partner-set audio surface and #227's twelve-partner-set video surface where partners ARE present) + request-side realtime-session-config opt-in (session.update event with voice/input_audio_format/output_audio_format/input_audio_transcription/turn_detection/tools/tool_choice/temperature/max_response_output_tokens/instructions/modalities:[text,audio] fields — the largest request-side opt-in axis-set yet, the union of every prior request-side opt-in across audio+image+video+chat-completion modalities) + CLI-subcommand-surface + slash-command-surface + pricing-tier-with-six-dimensional-compound-cost-model (per-model × per-modality-input × per-modality-output × per-cached-vs-fresh × per-audio-vs-text × per-minute-session-overhead — the largest pricing-tier extension yet, exceeding #227's five-dimensional and #228's four-dimensional matrices) + persistent-WebSocket-connection-transport-axis (NOVEL TENTH layer, distinct from every prior cluster member's HTTP-shaped transport — synchronous-HTTP for #211-#220+#222+#224, SSE-streaming for #213 partial subsets, multipart-form-data-HTTP for #223+#225+#226+#227+#228 binary-upload subsets, async-task-polling-HTTP for #221+#227+#228 — the cluster has now exhausted EVERY HTTP-shaped transport, and #229 introduces the FIRST non-HTTP transport, requiring WebSocket-upgrade-request-with-subprotocol-negotiation + bidirectional-frame-multiplexing-with-text+binary-frames + ping/pong-keepalive + graceful-close-with-status-code-and-reason + reconnection-with-resumption-token + per-event-type-JSON-envelope-dispatch-with-37+-event-types-on-a-single-connection + backpressure-handling-on-both-directions + authentication-via-Authorization-header-on-the-upgrade-request-and-per-session-token-rotation — none of which any HTTP-only transport requires) + bidirectional-symmetric-event-pair shape (input_audio_buffer.append → conversation.item.created, response.create → response.audio.delta + response.audio.done + response.audio_transcript.delta + response.audio_transcript.done + response.function_call_arguments.delta + response.function_call_arguments.done + response.done) — making #229 the FIRST cluster member that introduces a non-HTTP transport (persistent-WebSocket), the FIRST cluster member where Provider trait return type must be a duplex-channel-pair, and the FIRST cluster member where session lifecycle exceeds a single request-response cycle (typical Realtime sessions last 1-30+ minutes with state accumulating across the connection) (Jobdori cycle #380 / extends #168c emission-routing audit / explicit follow-on from #225 audio-bidirectional axis and #228 confirmed-structural async-task-polling cluster — introduces a NOVEL TRANSPORT axis distinct from every prior cluster member / sibling-shape cluster grows to twenty-eight / wire-format-parity cluster grows to nineteen / capability-parity cluster grows to eleven / multimodal-IO cluster grows to seven: #220 image-input + #224 embedding-output + #225 audio-bidirectional-on-separate-REST-endpoints + #226 image-output + #227 video-output + #228 mesh-output + #229 audio-text-tool-multiplex-on-persistent-WebSocket / provider-asymmetric-delegation cluster grows to six / async-task-polling cluster: still 3 members (#229 is push-based not poll-based — it does NOT join async-task-polling cluster, it founds a NEW cluster) / Persistent-WebSocket-transport cluster: 1 member (#229 alone, FOUNDER) / Bidirectional-symmetric-event-pair cluster: 1 member (#229 alone, FOUNDER) / Non-HTTP-transport cluster: 1 member (#229 alone, FOUNDER) — three new clusters founded in a single pinpoint, the first time a single cycle has founded three concurrent novel clusters / ten-layer-fusion-shape-with-persistent-WebSocket-transport-and-bidirectional-symmetric-event-pair is the largest single-pinpoint fusion catalogued. Distinct from prior cluster members; the ten-layer-fusion-shape with persistent-WebSocket-transport and bidirectional-symmetric-event-pair shape is novel and applies to follow-on candidate Real-time-Image-Generation API typed taxonomy (DALL-E live preview, Imagen live preview) and Real-time-Video-Generation streaming (Veo-Live, Sora-Live) — the persistent-WebSocket-transport pattern is now a first-class cluster member, a structural prerequisite that every future endpoint family using persistent connections will inherit / external validation: forty-eight ecosystem references covering OpenAI Realtime API GA 2024-10-01 with /v1/realtime?model=<id> WebSocket endpoint, 37+ canonical event-type names in OpenAI Realtime API spec, two transport options (WebSocket server-side and WebRTC browser-side), two GA realtime models (gpt-4o-realtime-preview and gpt-4o-mini-realtime-preview both with audio modality and tool-use), Google Gemini Live API with bidirectional WebSocket+gRPC streaming, Azure OpenAI Realtime API mirror, OpenAI Python SDK openai.realtime.AsyncRealtimeConnection typed client, OpenAI TypeScript SDK OpenAI.beta.realtime.RealtimeClient typed client, openai-realtime-api-beta reference client (canonical JS implementation), five first-class realtime-voice-agent frameworks all built on top of OpenAI Realtime API (Vapi/Retell-AI/LiveKit-Agents/Pipecat/Daily-Bots), Anthropic non-coverage statement (the second post-#224 provider-asymmetric-delegation case after audio), the canonical six-dimensional pricing matrix ($5.00/$20.00 per million text input/output tokens, $40.00/$80.00 per million audio input/output tokens, $2.50 per million cached audio input tokens for gpt-4o-realtime-preview-2024-10-01), coding-agent peer landscape: anomalyco/opencode has zero GA realtime integration (open feature request from 2026-02 only — confirmed via web search 2026-04-26), sst/opencode predecessor zero realtime, charmbracelet/crush zero realtime, continue.dev zero realtime, aider zero realtime, cursor zero realtime, zed zero realtime — the gap is uniformly zero across the surveyed ecosystem and represents the next-frontier capability that every coding-agent will need to add. claw-code is one of MULTIPLE clients without Realtime, but the persistent-WebSocket-transport-axis is the upstream prerequisite of every voice-agent / live-coding-pair-programming / push-to-talk-coding / barge-in-coding-conversation / function-call-during-voice / streaming-tool-use / sub-second-latency-coding-interaction affordance — the canonical 2024-2026-era voice-coding workflow that is currently impossible to build on top of claw-code — #229 closes the upstream prerequisite of every voice-coding affordance and is the first cluster member where transport-axis becomes a structural prerequisite of the dispatch layer)
2026-04-26 04:40:50 +09:00

Claw Code

ultraworkers/claw-code · Usage · Error Handling · Rust workspace · Parity · Roadmap · UltraWorkers Discord

Star history for ultraworkers/claw-code

Claw Code

Claw Code is the public Rust implementation of the claw CLI agent harness. The canonical implementation lives in rust/, and the current source of truth for this repository is ultraworkers/claw-code.

Important

Start with USAGE.md for build, auth, CLI, session, and parity-harness workflows. Make claw doctor your first health check after building, use rust/README.md for crate-level details, read PARITY.md for the current Rust-port checkpoint, and see docs/container.md for the container-first workflow.

ACP / Zed status: claw-code does not ship an ACP/Zed daemon entrypoint yet. Run claw acp (or claw --acp) for the current status instead of guessing from source layout; claw acp serve is currently a discoverability alias only, and real ACP support remains tracked separately in ROADMAP.md.

Current repository shape

  • rust/ — canonical Rust workspace and the claw CLI binary
  • USAGE.md — task-oriented usage guide for the current product surface
  • ERROR_HANDLING.md — unified error-handling pattern for orchestration code
  • PARITY.md — Rust-port parity status and migration notes
  • ROADMAP.md — active roadmap and cleanup backlog
  • PHILOSOPHY.md — project intent and system-design framing
  • SCHEMAS.md — JSON protocol contract (Python harness reference)
  • src/ + tests/ — companion Python/reference workspace and audit helpers; not the primary runtime surface

Quick start

Note

[!WARNING] cargo install claw-code installs the wrong thing. The claw-code crate on crates.io is a deprecated stub that places claw-code-deprecated.exe — not claw. Running it only prints "claw-code has been renamed to agent-code". Do not use cargo install claw-code. Either build from source (this repo) or install the upstream binary:

cargo install agent-code   # upstream binary — installs 'agent.exe' (Windows) / 'agent' (Unix), NOT 'agent-code'

This repo (ultraworkers/claw-code) is build-from-source only — follow the steps below.

# 1. Clone and build
git clone https://github.com/ultraworkers/claw-code
cd claw-code/rust
cargo build --workspace

# 2. Set your API key (Anthropic API key — not a Claude subscription)
export ANTHROPIC_API_KEY="sk-ant-..."

# 3. Verify everything is wired correctly
./target/debug/claw doctor

# 4. Run a prompt
./target/debug/claw prompt "say hello"

Note

Windows (PowerShell): the binary is claw.exe, not claw. Use .\target\debug\claw.exe or run cargo run -- prompt "say hello" to skip the path lookup.

Windows setup

PowerShell is a supported Windows path. Use whichever shell works for you. The common onboarding issues on Windows are:

  1. Install Rust first — download from https://rustup.rs/ and run the installer. Close and reopen your terminal when it finishes.
  2. Verify Rust is on PATH:
    cargo --version
    
    If this fails, reopen your terminal or run the PATH setup from the Rust installer output, then retry.
  3. Clone and build (works in PowerShell, Git Bash, or WSL):
    git clone https://github.com/ultraworkers/claw-code
    cd claw-code/rust
    cargo build --workspace
    
  4. Run (PowerShell — note .exe and backslash):
    $env:ANTHROPIC_API_KEY = "sk-ant-..."
    .\target\debug\claw.exe prompt "say hello"
    

Git Bash / WSL are optional alternatives, not requirements. If you prefer bash-style paths (/c/Users/you/... instead of C:\Users\you\...), Git Bash (ships with Git for Windows) works well. In Git Bash, the MINGW64 prompt is expected and normal — not a broken install.

Post-build: locate the binary and verify

After running cargo build --workspace, the claw binary is built but not automatically installed to your system. Here's where to find it and how to verify the build succeeded.

Binary location

After cargo build --workspace in claw-code/rust/:

Debug build (default, faster compile):

  • macOS/Linux: rust/target/debug/claw
  • Windows: rust/target/debug/claw.exe

Release build (optimized, slower compile):

  • macOS/Linux: rust/target/release/claw
  • Windows: rust/target/release/claw.exe

If you ran cargo build without --release, the binary is in the debug/ folder.

Verify the build succeeded

Test the binary directly using its path:

# macOS/Linux (debug build)
./rust/target/debug/claw --help
./rust/target/debug/claw doctor

# Windows PowerShell (debug build)
.\rust\target\debug\claw.exe --help
.\rust\target\debug\claw.exe doctor

If these commands succeed, the build is working. claw doctor is your first health check — it validates your API key, model access, and tool configuration.

Optional: Add to PATH

If you want to run claw from any directory without the full path, choose one of these approaches:

Option 1: Symlink (macOS/Linux)

ln -s $(pwd)/rust/target/debug/claw /usr/local/bin/claw

Then reload your shell and test:

claw --help

Option 2: Use cargo install (all platforms)

Build and install to Cargo's default location (~/.cargo/bin/, which is usually on PATH):

# From the claw-code/rust/ directory
cargo install --path . --force

# Then from anywhere
claw --help

Option 3: Update shell profile (bash/zsh)

Add this line to ~/.bashrc or ~/.zshrc:

export PATH="$(pwd)/rust/target/debug:$PATH"

Reload your shell:

source ~/.bashrc  # or source ~/.zshrc
claw --help

Troubleshooting

  • "command not found: claw" — The binary is in rust/target/debug/claw, but it's not on your PATH. Use the full path ./rust/target/debug/claw or symlink/install as above.
  • "permission denied" — On macOS/Linux, you may need chmod +x rust/target/debug/claw if the executable bit isn't set (rare).
  • Debug vs. release — If the build is slow, you're in debug mode (default). Add --release to cargo build for faster runtime, but the build itself will take 510 minutes.

Note

Auth: claw requires an API key (ANTHROPIC_API_KEY, OPENAI_API_KEY, etc.) — Claude subscription login is not a supported auth path.

Run the workspace test suite after verifying the binary works:

cd rust
cargo test --workspace

Documentation map

Ecosystem

Claw Code is built in the open alongside the broader UltraWorkers toolchain:

Ownership / affiliation disclaimer

  • This repository does not claim ownership of the original Claude Code source material.
  • This repository is not affiliated with, endorsed by, or maintained by Anthropic.
Description
The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars . Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.
Readme 60 MiB
Languages
Rust 96.4%
Python 3.2%
Shell 0.4%