内容

<img src="docs/assets/readme/banner.jpg" alt="CLI-JAW — your personal AI agent. Every AI CLI, one dashboard." width="100%"> One assistant, one memory, one dashboard for the AI coding CLIs you already pay for. Claude, Codex, Cursor, Grok, Copilot, OpenCode, Kiro, Antigravity and Pi — working together as a team. <a href="https://npmjs.com/package/cli-jaw"><img src="https://img.shields.io/npm/v/cli-jaw?color=cb3837&label=npm&logo=npm" alt="npm version"></a> <a href="https://github.com/lidge-ai/cli-jaw/releases/latest"><img src="https://img.shields.io/github/v/release/lidge-ai/cli-jaw?label=release" alt="latest release"></a> <img src="https://img.shields.io/badge/node-%3E%3D22.4-339933?logo=node.js&logoColor=white" alt="Node.js 22.4+"> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue" alt="MIT license"></a> ```bash # existing users who want minimal changes: JAW_SAFE=1 npm install -g cli-jaw npm install -g cli-jaw jaw dashboard ``` <a href="https://github.com/lidge-ai/cli-jaw/releases/latest"><img src="https://img.shields.io/badge/macOS-.dmg-24292f?logo=apple&logoColor=white" alt="Download for macOS (.dmg)"></a> <a href="https://github.com/lidge-ai/cli-jaw/releases/latest"><img src="https://img.shields.io/badge/Windows-.exe-24292f?logo=windows&logoColor=white" alt="Download for Windows (.exe)"></a> <a href="https://github.com/lidge-ai/cli-jaw/releases/latest"><img src="https://img.shields.io/badge/Linux-.AppImage-24292f?logo=linux&logoColor=white" alt="Download for Linux (.AppImage)"></a> <table> <tr> <td width="50%" valign="middle"> ### Every agent in one place Start, stop and preview every running instance from the manager dashboard. </td> <td width="50%"><img src="docs/screenshots/manager-dashboard-light.png" alt="CLI-JAW manager dashboard" width="100%"></td> </tr> <tr> <td width="50%" valign="middle"> ### A board for the work Kanban lanes, a priority matrix and reminders track what each session is doing. </td> <td width="50%"><img src="docs/screenshots/dashboard-kanban.png" alt="Kanban board of agent sessions" width="100%"></td> </tr> <tr> <td width="50%" valign="middle"> ### Notes that agents can read A built-in Markdown workspace with WYSIWYG editing, math and Mermaid diagrams. </td> <td width="50%"><img src="docs/screenshots/notes-wysiwyg.png" alt="Notes editor" width="100%"></td> </tr> </table> English · <a href="README.ko.md">한국어</a> · <a href="README.zh-CN.md">中文</a> · <a href="README.ja.md">日本語</a> · 📖 <a href="https://lidge-ai.github.io/cli-jaw/">Website</a> · <a href="https://lidge-ai.github.io/cli-jaw/dev/">Docs</a> --- ## What is CLI-JAW? CLI-JAW unifies the AI coding CLIs you already use into **one assistant with one memory and one dashboard**. Your main CLI (the "Boss") calls the others as "employees", so you stop copy-pasting between apps and give orders from a single place. - **No API keys needed** — routes through subscriptions you already pay for - **No per-token billing** — flat monthly cost, same as what you already have - **Runs locally** — your code never leaves your machine - **Reach it anywhere** — Web, desktop app, terminal, Telegram, Discord or Slack The native Code API (`/api/code`) provides isolated Codex, Claude, Cursor, and Grok sessions with durable transcripts and native resume. See [native Code sessions](structure/runtime-integration.md#native-code-sessions). --- ## Install <details> <summary>Safe install — for existing users who want minimal changes</summary> ```bash # macOS / Linux JAW_SAFE=1 npm install -g cli-jaw # skips optional tool/runtime setup jaw init # interactive setup later when you're ready ```  **Windows support.** WSL is the recommended, stable path. A native PowerShell installer also exists, but it is still **beta**: ```powershell irm https://raw.githubusercontent.com/lidge-ai/cli-jaw/main/scripts/install.ps1 | iex ``` Requires Node.js 22.4+. The manager dashboard runs on **24576**, and each agent web UI on **3457**. If a restrictive execution policy blocks `jaw.ps1`, use the `.cmd` entry point instead of loosening the policy: ```powershell jaw.cmd doctor ``` Native Windows autostart is registered through the windows-startup backend. `jaw service install` also covers macOS (launchd) and Linux (systemd).  Either way cli-jaw now tells the two apart precisely: `jaw doctor --json` reports `platform` as `windows-native` or `wsl`, and each gets its own diagnostics. Native Windows no longer receives "reinstall inside WSL" advice just because WSL interop is configured on the machine. </details> ```bash # macOS / Linux / WSL with Node.js 22+ already installed npm install -g cli-jaw jaw dashboard ``` > **npm 12+?** npm now blocks dependency install scripts by default. If you see `npm warn allow-scripts`, install with the scripts approved: > > ```bash > npm install -g cli-jaw --allow-scripts=cli-jaw > ``` <details> <summary>Windows npm install recovery — npm 12+ blocked scripts or PowerShell execution policy</summary> npm 12+ may finish a global install while blocking CLI-JAW's dependency `postinstall`. Approve only this package and reinstall, or save the approval for future upgrades: ```powershell npm install -g cli-jaw --allow-scripts=cli-jaw npm config set allow-scripts=cli-jaw --location=user jaw doctor ``` If PowerShell reports that `jaw.ps1` cannot be loaded because script execution is disabled, choose one of these bounded workarounds: ```powershell Set-ExecutionPolicy -Scope CurrentUser RemoteSigned jaw.cmd doctor node "$(npm prefix -g)\node_modules\cli-jaw\dist\bin\cli-jaw.js" doctor ``` `jaw.ps1` is PowerShell's npm shim and is subject to execution policy; `jaw.cmd` is the equivalent cmd shim and does not use that policy. The direct `node` form bypasses both shims. `jaw doctor` reports a blocked/stale install, leftover npm staging directories, and the current PowerShell policy; it also prints the matching recovery guidance. </details> That's it. Open **http://localhost:24576** for the manager dashboard. Per-instance agent Web UIs still run from **http://localhost:3457** when you start `jaw serve`. Requires [Node.js 22.4+](https://nodejs.org). > **First time?** The default npm install initializes CLI-JAW and attempts native Claude setup. Other AI CLIs are optional; install them all during npm setup with `CLI_JAW_INSTALL_CLI_TOOLS=1 npm install -g cli-jaw` on macOS/Linux. On Windows, use the WSL install path below. > **Retired runtimes.** Claude E (`claude-e`) and the AI-E multiplexer (`ai-e`) have been removed. A saved selection stays visible as retired and cannot execute; choose an available runtime. Details: [runtime integration](structure/runtime-integration.md). <details> <summary>macOS one-click — don't have Node.js? This installs everything</summary> ```bash curl -fsSL https://raw.githubusercontent.com/lidge-ai/cli-jaw/main/scripts/install.sh | bash source "${ZDOTDIR:-$HOME}/.zshrc" 2>/dev/null || true bash "$(npm root -g)/cli-jaw/scripts/verify-fresh-install.sh" ``` </details> <details> <summary>Windows (WSL — Windows Subsystem for Linux) — one-click from scratch</summary> ```powershell # 1. Install WSL (PowerShell as Admin) wsl --install ``` Restart, open **Ubuntu**, then: ```bash # 2. Install CLI-JAW + all dependencies curl -fsSL https://raw.githubusercontent.com/lidge-ai/cli-jaw/main/scripts/install-wsl.sh | bash source ~/.bashrc jaw dashboard bash "$(npm root -g)/cli-jaw/scripts/verify-fresh-install.sh" ``` From Windows PowerShell into WSL, run commands through a login shell so the WSL profile PATH is loaded: ```powershell wsl.exe -d Ubuntu -- bash -lc "jaw dashboard" ``` </details> <details> <summary>Native Windows (PowerShell beta) — detached server logs</summary> `jaw serve` preserves the stdout and stderr streams it inherits and also appends both streams to `<JAW_HOME>\logs\serve.log`. At startup, a file already at 5 MiB is rotated once to `serve.log.1`. Native Windows still does not have a registered `jaw service` logging backend. PowerShell's `Start-Process -RedirectStandardOutput/-RedirectStandardError` creates or truncates its target files on every launch, so do not point those options at the instance-owned `serve.log`. If separate operator-owned stdout/stderr files are needed, run the redirection inside a child PowerShell process instead. This example appends them under `<JAW_HOME>\logs` without the `Start-Process` truncate default: ```powershell $jawHome = 'C:\jaw\worker-a' $port = 3458 $logDir = Join-Path $jawHome 'logs' $outLog = Join-Path $logDir 'serve.out.log' $errLog = Join-Path $logDir 'serve.err.log' New-Item -ItemType Directory -Force -Path $logDir -ErrorAction Stop | Out-Null foreach ($path in @($outLog, $errLog)) { # OpenOrCreate preserves existing content while proving that the child can append. $probe = [IO.File]::Open($path, 'OpenOrCreate', 'Write', 'ReadWrite') $probe.Dispose() } $jaw = (Get-Command jaw.cmd -ErrorAction Stop).Source $childCommand = "& '$jaw' --home '$jawHome' serve --port $port --no-open 1>> '$outLog' 2>> '$errLog'" $encoded = [Convert]::ToBase64String([Text.Encoding]::Unicode.GetBytes($childCommand)) Start-Process -FilePath powershell.exe -ArgumentList '-NoProfile', '-EncodedCommand', $encoded -WindowStyle Hidden | Out-Null ``` Read each stream from a separate PowerShell terminal (`Get-Content -Wait` occupies its terminal). These commands use explicit paths because variables from the launch terminal are not available in a new PowerShell session: ```powershell # Terminal 1 Get-Content -LiteralPath 'C:\jaw\worker-a\logs\serve.out.log' -Tail 100 -Wait # Terminal 2 Get-Content -LiteralPath 'C:\jaw\worker-a\logs\serve.err.log' -Tail 100 -Wait ``` Lifecycle commands are home-scoped and verify `<JAW_HOME>\jaw.pid.json` before signalling: ```powershell & $jaw --home $jawHome service stop --port $port & $jaw --home $jawHome service restart --port $port ``` A standalone `service restart` safely relaunches the instance detached, but cannot recreate the operator's file redirection. To preserve file capture, `stop`, optionally rotate the closed logs, and run the launch block again: ```powershell $pidFile = Join-Path $jawHome 'jaw.pid.json' $serverProcess = $null if (Test-Path -LiteralPath $pidFile -PathType Leaf) { $record = Get-Content -LiteralPath $pidFile -Raw -ErrorAction Stop | ConvertFrom-Json $serverProcess = Get-Process -Id ([int]$record.pid) -ErrorAction SilentlyContinue } & $jaw --home $jawHome service stop --port $port if ($LASTEXITCODE -ne 0) { throw "jaw service stop failed with exit code $LASTEXITCODE" } if ($serverProcess) { try { if (-not $serverProcess.WaitForExit(5000)) { throw "jaw serve pid $($serverProcess.Id) did not exit within 5000ms" } } finally { $serverProcess.Dispose() } } $stamp = Get-Date -Format 'yyyyMMdd-HHmmss' foreach ($path in @($outLog, $errLog)) { if (Test-Path -LiteralPath $path) { Move-Item -LiteralPath $path -Destination "$path.$stamp" -ErrorAction Stop } } # Run the Start-Process launch block above again. ``` Do not use `Get-Process node | Stop-Process`; it can terminate unrelated cli-jaw instances and AI runtime processes. </details> <details> <summary>Fresh-machine evidence — maintainer release check</summary> Run this on a clean VM before publishing installer changes. It writes environment snapshots, installer logs, the exact collector/installer/verifier scripts that ran, their SHA-256 hashes, verifier logs, and new-shell PATH probes into `~/cli-jaw-fresh-install-evidence-*`. ```bash # macOS Terminal COLLECTOR=/tmp/cli-jaw-collect-fresh-install-evidence.sh curl -fsSL https://raw.githubusercontent.com/lidge-ai/cli-jaw/main/scripts/collect-fresh-install-evidence.sh -o "$COLLECTOR" bash "$COLLECTOR" --target macos # Ubuntu inside WSL COLLECTOR=/tmp/cli-jaw-collect-fresh-install-evidence.sh bash "$COLLECTOR" --target wsl ``` From Windows PowerShell, enter the supported WSL path: ```powershell wsl.exe -d Ubuntu -- bash -lc 'COLLECTOR=/tmp/cli-jaw-collect-fresh-install-evidence.sh; curl -fsSL https://raw.githubusercontent.com/lidge-ai/cli-jaw/main/scripts/collect-fresh-install-evidence.sh -o "$COLLECTOR"; bash "$COLLECTOR" --target wsl' ``` If the collector says `powershell.exe` is not available inside WSL, run this from Windows PowerShell before auditing: ```powershell wsl.exe -d Ubuntu -- bash -lc 'EVIDENCE_DIR="$(ls -dt ~/cli-jaw-fresh-install-evidence-* | head -1)"; { echo "command=wsl.exe -d Ubuntu -- bash -lc jaw --version"; jaw --version; } | tee "$EVIDENCE_DIR/33-powershell-to-wsl-probe.log"' ``` For an unmerged branch or local VM checkout, pass the local installer and verifier explicitly: ```bash bash scripts/collect-fresh-install-evidence.sh --target macos --install-script scripts/install.sh --verifier-script scripts/verify-fresh-install.sh bash scripts/collect-fresh-install-evidence.sh --target wsl --install-script scripts/install-wsl.sh --verifier-script scripts/verify-fresh-install.sh ``` Audit each collected directory before treating it as target evidence: ```bash EVIDENCE_DIR="$(ls -dt ~/cli-jaw-fresh-install-evidence-* | head -1)" AUDITOR="$(npm root -g)/cli-jaw/scripts/audit-fresh-install-evidence.mjs" node "$AUDITOR" "$EVIDENCE_DIR" --target macos node "$AUDITOR" "$EVIDENCE_DIR" --target wsl # For a local checkout, audit with the checkout's auditor: node scripts/audit-fresh-install-evidence.mjs "$EVIDENCE_DIR" --target macos node scripts/audit-fresh-install-evidence.mjs "$EVIDENCE_DIR" --target wsl ``` Before publishing installer changes, run the matrix gate with both strict evidence directories: ```bash GATE="$(npm root -g)/cli-jaw/scripts/verify-release-evidence.mjs" node "$GATE" --macos /path/to/macos-evidence --wsl /path/to/wsl-evidence # For a local checkout: node scripts/verify-release-evidence.mjs --macos /path/to/macos-evidence --wsl /path/to/wsl-evidence ``` The matrix gate rejects evidence collected with stale collector, installer, or verifier scripts; archived evidence scripts must match the current package or checkout that runs the gate. When `scripts/promote-to-main.sh`, `scripts/release-preview.sh`, or `npm publish` detects installer-sensitive changes since the previous tag, it runs this same matrix gate before any git push or npm publish. Set the evidence directories before starting a release: ```bash CLI_JAW_MACOS_EVIDENCE_DIR=/path/to/macos-evidence \ CLI_JAW_WSL_EVIDENCE_DIR=/path/to/wsl-evidence \ bash scripts/promote-to-main.sh ``` `scripts/promote-to-main.sh` promotes **only an already-certified `preview` head**. It refuses to start unless a successful `test.yml` push run exists for that exact `preview` SHA. With no argument it promotes the live `origin/preview` head; an optional SHA argument must equal that same head, so it acts as an assertion rather than a way to promote an older commit. The script dispatches the npm publish and then exits without checking whether the publish succeeded, and it cannot be re-run afterwards. Recovery for a partially completed release — npm publish missing, GitHub release missing, a bad version on `latest`, or a red commit on `main` — is documented in [`structure/infra.md` § 릴리스 파이프라인과 부분 실패 복구](structure/infra.md#릴리스-파이프라인과-부분-실패-복구-preview--main--npm). </details> <details> <summary>Docker</summary> ```bash docker compose up -d # → http://localhost:3457 ``` </details> --- ## Authenticate You only need **one**. Pick whichever subscription you already have: ```bash # Free options (no credit card needed) copilot login # GitHub Copilot (free tier available) opencode # OpenCode — free models available kiro # AWS Kiro (free tier with AWS account) # Paid (monthly subscription you already pay for) claude auth login # Anthropic Claude Pro or higher codex login # OpenAI ChatGPT Pro or higher cursor-agent login # Cursor grok login --oauth # xAI Grok / Grok Heavy ``` Check everything at once: `jaw doctor` <details> <summary>Example jaw doctor output</summary> ``` 🦈 CLI-JAW Doctor — 13 checks ✅ Node.js v22.15.0 ✅ Claude CLI installed ✅ Codex CLI installed ✅ Cursor CLI installed ✅ OpenCode CLI installed ✅ Copilot CLI installed ✅ Database jaw.db OK ✅ Skills 29 active, 238 reference ✅ MCP (plugins) 3 servers configured ✅ Memory structured/ exists ✅ Server port 3457 available ``` </details> --- ## What you get ### Employees: your CLI calls the others You talk to one AI (the "Boss"). When it needs specialized work, it dispatches tasks to employees — each running its own CLI and model — and reviews their output before answering you. ```text You: "Fix the frontend styling and update the API endpoint" Boss (Claude) ├── Frontend employee (OpenCode) → "Fix the CSS grid layout in dashboard.tsx" ├── Backend employee (Codex) → "Update /api/users to return pagination metadata" └── Synthesizes both results for you ``` ```bash jaw dispatch --agent "Backend" --task "Run read-only verification" --watch jaw dispatch --virtual "security" --task "Review this branch for auth and secret leaks" --watch ``` ### PABCD: plan, audit, build, check, done For complex tasks CLI-JAW runs a structured workflow. You approve every transition; read-only workers verify the plan and the result. | Phase | What happens | |---|---| | **P — Plan** | Boss writes a diff-level plan and stops for your review | | **A — Audit** | A read-only worker checks the plan is feasible | | **B — Build** | Boss implements; a read-only worker verifies | | **C — Check** | Type-check, docs update, consistency check | | **D — Done** | Summary of all changes, back to idle | State survives restarts. Start with `jaw orchestrate` or `/pabcd`, resume with `/continue`, and keep long objectives alive with `/goal`. See [PABCD](https://lidge-ai.github.io/cli-jaw/dev/concepts/pabcd.html). ### Memory, skills and MCP - **Three memory layers** — recent session history, structured notes flushed from conversations, and a searchable soul/task snapshot: `jaw memory search "how did we set up the API auth?"` - **200+ skills** — office documents (PDF, DOCX, XLSX, PPTX, HWP), browser and desktop automation, media, GitHub, Notion and dev guides: `jaw skill install <name>` - **One MCP config for every engine** — `jaw mcp install @anthropic/context7` syncs Claude, Codex, Kiro, OpenCode, Copilot and Antigravity at once ### Browser and desktop automation Drive Chrome through the DevTools Protocol, click by description with `jaw browser vision-click "Login button"`, and control desktop apps through the `jaw-computer-use` MCP tool (or Codex's native Computer Use plugin) on supported macOS and Windows hosts. Ask ChatGPT, Gemini or Grok web UIs with `jaw browser web-ai`. ### Messaging Chat with your agent from **Telegram** (voice messages, forum topics, scheduled heartbeat jobs), **Discord** and **Slack** (Socket Mode, threads, file relay, mention watching). Enable several channels at once; the home channel receives proactive sends. <details> <summary>Telegram setup (3 steps)</summary> 1. Message [@BotFather](https://t.me/BotFather) → `/newbot` → copy the token 2. `jaw init --telegram-token YOUR_TOKEN` or use Web UI settings 3. Send any message to your bot. Chat ID is auto-saved on first message </details> <details> <summary>Slack setup (guided wizard)</summary> 1. `jaw slack setup` — prints the app manifest, opens the Slack app page, validates both tokens live and writes the settings 2. `/invite @cli-jaw` in each channel the bot should read, then restart `jaw serve` Group DMs need the `message.mpim` event and `mpim:history` scope. For containers, `SLACK_BOT_TOKEN`, `SLACK_APP_TOKEN`, `SLACK_TEAM_ID` and `SLACK_CHANNEL_IDS` own their fields at runtime. Details: [Slack tools](docs/slack-tools.md). </details> ### Desktop app The Electron app boots the manager dashboard, ships a bundled Node.js sidecar, and lives in your menu bar. Download it from [GitHub Releases](https://github.com/lidge-ai/cli-jaw/releases/latest): Each desktop build verifies its bundled server starts successfully before installers are uploaded. - **macOS (Apple Silicon)** — open the DMG and drag CLI-JAW into Applications. Builds are Developer ID signed, notarized and stapled, and update in-app. - **Windows (x64)** — run the Setup `.exe`. It is unsigned, so SmartScreen may ask you to confirm. - **Linux (x64)** — make the AppImage executable and run it. After first launch, accept **Install CLI command** (or use the tray item **Install CLI to Terminal**) to get `jaw` in your terminal without a global npm install. --- ## AI runtimes No per-token API billing. Route through subscriptions you already pay for. | CLI | Default model | Auth | Cost | |---|---|---|---| | **Pi** | `grok-composer-2.5-fast` | Settings profile API key, local proxy, or `PI_CODING_AGENT_BIN` | Local/API endpoints through an isolated profile | | **Claude** | `claude-opus-4-8` | `claude auth login` | Claude Pro subscription or higher | | **Antigravity** | AGY-selected | checked by `agy` at run time | Experimental print-mode runtime | | **Codex** | `gpt-5.5` | `codex login` | ChatGPT Pro subscription or higher | | **Codex App** | `gpt-5.5` | `codex login` | ChatGPT Pro subscription or higher | | **Cursor** | `composer-2.5` | `cursor-agent login` or `CURSOR_API_KEY` | Cursor subscription | | **Grok** | `grok-build` | `grok login --oauth` | Grok subscription | | **Kiro** | registry-selected | `kiro` | AWS Kiro free tier | | **OpenCode** | `opencode-go/kimi-k2.6` | `opencode` | Free models available | | **Copilot** | `claude-sonnet-4.6` | `copilot login` | Free tier available | If one engine is rate-limited the next picks up (`/fallback`). Switch engines live with `/cli codex` and models with `/model gpt-5.5` — from Web, Terminal, Telegram, Discord, or Slack. --- ## CLI ```bash # Core jaw dashboard # launch manager dashboard jaw serve # start an agent server (http://localhost:3457) jaw chat # terminal chat UI jaw ask "question" # one prompt, one answer — no TTY needed jaw doctor # installation and runtime diagnostics # Instances jaw clone ~/project # clone instance to new directory jaw --home ~/project serve --port 3458 # run a second instance jaw service install # auto-start on boot (macOS launchd / Linux systemd) jaw --home ~/project service restart --port 3458 # restart only this instance # Agents and workflow jaw employee list jaw dispatch --agent "Backend" --task "..." --watch jaw orchestrate # PABCD workflow jaw goal status # persistent goals # Skills, MCP, memory, browser jaw skill list jaw mcp install <package> jaw memory search <query> jaw browser fetch "https://example.com" --json ``` Each instance created with `jaw clone` has its own settings, memory, database and MCP config, and the manager dashboard sees them all. Remote and headless hosts: [structure/remote-headless.md](structure/remote-headless.md). Full command reference: [CLI docs](https://lidge-ai.github.io/cli-jaw/dev/reference/cli.html). --- ## Documentation | Topic | Where | |---|---| | Website and quickstart | [lidge-ai.github.io/cli-jaw](https://lidge-ai.github.io/cli-jaw/) | | Guides, concepts, reference | [Developer docs](https://lidge-ai.github.io/cli-jaw/dev/) | | Architecture | [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) · [structure/](structure/) | | Slack tools and local API | [docs/slack-tools.md](docs/slack-tools.md) | | Runtime integration (including retired runtimes) | [structure/runtime-integration.md](structure/runtime-integration.md) | --- ## Development ```bash npm run build # tsc → dist/ npm run build:frontend # vite → public/dist/ npm run dev # tsx server.ts (hot-reload) npm test # node:test driver (tests/run.mts) npm run gate:all # release/docs parity gates npm run electron:dev # desktop app with hot reload ``` --- ## Troubleshooting | Problem | Solution | |---|---| | `cli-jaw: command not found` | `npm install -g cli-jaw` again. macOS/Linux/WSL: check `~/.local/bin` or `npm prefix -g` + `/bin` is in `$PATH`. From Windows PowerShell, invoke WSL through a login shell: `wsl.exe -d Ubuntu -- bash -lc "jaw dashboard"`. | | `npm warn allow-scripts ...` | npm >= 12 blocks dependency install scripts: `npm install -g cli-jaw --allow-scripts=cli-jaw`, or persist with `npm config set allow-scripts=cli-jaw --location=user`. Already installed? `jaw init` finishes setup. | | pnpm/bun blocked build scripts | pnpm 11+: `pnpm add -g --allow-build=cli-jaw cli-jaw`. bun: `bun add -g --trust cli-jaw`. | | Fresh install verifier fails | Fix the reported PATH or executable-bit issue, then rerun `bash "$(npm root -g)/cli-jaw/scripts/verify-fresh-install.sh"`. | | `Error: node version` | Upgrade to Node.js 22.4+: `nvm install 22` | | `NODE_MODULE_VERSION` mismatch | `npm run ensure:native` | | `EADDRINUSE: port 3457` | Another instance is running. Use `--port 3458` or stop it first | | Telegram / Discord / Slack auth fails | Run `jaw doctor`, check tokens, restart `jaw serve` | | Employee dispatch hangs | `jaw employee list`, make sure the employee CLI is authenticated (`jaw doctor`), retry with `jaw dispatch --watch` | --- ## Contributing Public code and product docs live here. Private planning and history live only in a separate sibling clone of [cli-jaw-internal](https://github.com/lidge-jun/cli-jaw-internal); request access through an [issue](https://github.com/lidge-ai/cli-jaw/issues). Do not create private records in this checkout, including `devlog`, `_plan`, `_fin`, or `.jwc` aliases, or include private record paths in public docs/source. Follow [local pre-push setup and checks](CONTRIBUTING.md#local-private-path-check) before uploading changes. 1. Fork and branch from `dev` 2. `npm run build && npm run build:frontend && npm test` 3. For release-sensitive changes, also run `npm run gate:all` 4. Submit a PR --- <a href="LICENSE">MIT License</a> · Built by developers who got tired of tab-switching between AI apps. ### Aside (experimental) Select Aside in Settings → Agent, then enter the local account ID and select a registered model. Model defaults uses the same account-scoped controls. You can also configure the explicit account selector: `perCli.aside = { "account": "u0", "host": "local", "model": "default", "effort": "default" }`. Catalog discovery reads only that account's allowlisted local model metadata; installed binary detection does not verify authentication. Safe uses guard; Auto uses full-access. Workers, memory flush, images, native Code and automatic retry/fallback are unsupported. Normal steer and `/steer` queue follow-ups; `/queue steer` is unavailable. If cleanup is uncertain, reconcile the captured session in Aside and acknowledge via `POST /api/orchestrate/aside/reconcile` with `{ "sessionId": "<jaw-chat-id>", "acknowledgementToken": "<retained-run-token>", "acknowledged": true }`. Recovery requires the captured local CLI to have closed and discards old queued input; send fresh input afterward. Stop does not prove external tools have physically finished.

cli-jaw

内容

连接信息

猜你喜欢

cli-jaw

微信扫一扫分享

需要认证

内容

连接信息

猜你喜欢