{"id":44752790,"url":"https://github.com/drpedapati/sciclaw","last_synced_at":"2026-05-05T07:03:01.706Z","repository":{"id":338687308,"uuid":"1156260107","full_name":"drpedapati/sciclaw","owner":"drpedapati","description":"Paired-scientist AI assistant for reproducible research — lightweight Go runtime, lifecycle hooks, manuscript integration, 12 baseline scientific skills. PicoClaw-compatible.","archived":false,"fork":false,"pushed_at":"2026-05-04T21:53:18.000Z","size":44803,"stargazers_count":64,"open_issues_count":22,"forks_count":10,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-05-04T23:39:51.815Z","etag":null,"topics":["ai-assistant","discord","golang","lifecycle-hooks","llm","paired-programming","picoclaw","quarto","reproducible-research","sciclaw","scientific-workflow"],"latest_commit_sha":null,"homepage":"https://sciclaw.dev","language":"Go","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/drpedapati.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"docs/security.html","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-12T12:56:00.000Z","updated_at":"2026-05-04T21:53:23.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/drpedapati/sciclaw","commit_stats":null,"previous_names":["drpedapati/sciclaw"],"tags_count":218,"template":false,"template_full_name":null,"purl":"pkg:github/drpedapati/sciclaw","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/drpedapati%2Fsciclaw","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/drpedapati%2Fsciclaw/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/drpedapati%2Fsciclaw/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/drpedapati%2Fsciclaw/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/drpedapati","download_url":"https://codeload.github.com/drpedapati/sciclaw/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/drpedapati%2Fsciclaw/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32639060,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-04T10:08:07.713Z","status":"online","status_checked_at":"2026-05-05T02:00:06.033Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-assistant","discord","golang","lifecycle-hooks","llm","paired-programming","picoclaw","quarto","reproducible-research","sciclaw","scientific-workflow"],"created_at":"2026-02-15T23:16:42.310Z","updated_at":"2026-05-05T07:03:01.658Z","avatar_url":"https://github.com/drpedapati.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n\u003cimg src=\"docs/philosophy-hero.jpg\" alt=\"sciClaw: A Partnership, Not a Platform\" width=\"760\" /\u003e\n\n\u003cbr /\u003e\n\n**A paired-scientist agent for reproducible research workflows.**\n\n[![Go](https://img.shields.io/badge/Go-1.25+-00ADD8?style=flat\u0026logo=go\u0026logoColor=white)](https://go.dev)\n[![Platforms](https://img.shields.io/badge/Platforms-macOS%20%C2%B7%20Linux%20%C2%B7%20Windows-blue)](https://github.com/drpedapati/sciclaw/releases)\n[![License](https://img.shields.io/badge/License-MIT-green)](LICENSE)\n[![Discord](https://img.shields.io/discord/1488473301889191977?logo=discord\u0026logoColor=white\u0026label=Discord\u0026color=5865F2)](https://discord.gg/UwGGGqU7yf)\n\n[Website](https://sciclaw.dev) ·\n[Documentation](https://sciclaw.dev/docs.html) ·\n[Manuscript (pending arXiv submission #7284050)](docs/assets/sciclaw-arxiv.pdf) ·\n[YouTube Tutorial](https://www.youtube.com/watch?v=P3pDulPnCzU) ·\n[Releases](https://github.com/drpedapati/sciclaw/releases) ·\n[Discord](https://discord.gg/UwGGGqU7yf) ·\n[Discussions](https://github.com/drpedapati/sciclaw/discussions)\n\n📬 [**Get email updates**](https://list.sciclaw.dev/subscription/form) — occasional release notes, no spam.\n\n\u003c/div\u003e\n\n---\n\nsciClaw is a paired-scientist agent for rigorous research work. It connects to major LLM providers, proposes and executes hypothesis-driven loops, runs real tools (literature, documents, shell), and keeps an auditable evidence trail in your workspace.\n\nBuilt on the [PicoClaw](https://github.com/sipeed/picoclaw) runtime (a Go rewrite of [nanobot](https://github.com/HKUDS/nanobot)), sciClaw keeps a single-binary footprint while adding a paired-scientist operating model: plan, evidence, review, iterate.\n\n## How You Talk to sciClaw\n\nThe most natural way to use sciClaw is through **Telegram** or **Discord**. You message it like you'd message a colleague. Ask a question, attach a file, get results back. No terminal, no special syntax.\n\n```\nYou:      \"Find recent papers on TDP-43 proteinopathy in ALS\"\nsciClaw:  [searches PubMed, returns 47 papers with citations, saves to workspace]\n\nYou:      \"Draft a methods section using the attached protocol\"\nsciClaw:  [produces a Word doc with tracked changes you review in Microsoft Word]\n```\n\nNew users should follow [Quick Start](#quick-start) below for the canonical setup path (install -\u003e initialize -\u003e authenticate -\u003e connect chat).\n\n\u003e **Prefer a visual interface?** Run `sciclaw app` to open an interactive dashboard in your terminal — no CLI knowledge needed. A CLI is also available for power users: `sciclaw agent -m \"your question\"` or `sciclaw agent` for interactive mode.\n\nDiscord on current `main`/dev builds also supports:\n- queued background jobs with status/cancel cards\n- `/btw` for explicit read-only side questions in the current workspace\n- `/skill` with workspace-aware autocomplete for explicit skill use\n- `/theme` to pick a response style (Clear, Formal, or Brief) that persists per user across sessions\n\n## Addons\n\nAddons are optional capabilities installed separately from the core binary. Each addon is a standalone repo with a manifest, a sidecar binary, and optional install scripts. The gateway reconciler spawns addon sidecars automatically and keeps them in sync.\n\nTwo reference addons ship under the sciclaw org (private repos):\n- **sciclaw-addon-webtop**: per-user Ubuntu XFCE browser desktops via Docker.\n- **sciclaw-addon-jupyter**: per-user Jupyter Lab servers with rotating token auth.\n\nAddons share the same workspace and user identity as your chat channels. Install with:\n\n```bash\nsciclaw addon install \u003curl\u003e --version v0.1.0\n```\n\nTen lifecycle commands: `install`, `enable`, `disable`, `uninstall`, `upgrade`, `verify`, `rollback`, `sbom`, `list`, `status`. The web UI injects sidebar tabs for each enabled addon. See the [dev log](docs/devlog.html) for implementation details.\n\n## Install\n\n### Homebrew (recommended)\n\n```bash\nbrew tap drpedapati/tap \u0026\u0026 brew install sciclaw\n```\n\nInstall surfaces are split intentionally:\n- `sciclaw.dev` is the website and documentation\n- `drpedapati/sciclaw` is the source repo and release binaries\n- `drpedapati/tap` is the Homebrew tap for `sciclaw`, `sciclaw-dev`, `irl`, and `sciclaw-*` companion formulas\n- `drpedapati/tools` is the Homebrew tap for standalone tools like `docx-review`, `pubmed-cli`, `pdf-form-filler`, and `phi-cleaner`\n\nIf you still have the old legacy tap installed, remove it to avoid ambiguity:\n\n```bash\nbrew untap drpedapati/sciclaw\n```\n\n### Homebrew (development channel)\n\n```bash\nbrew tap drpedapati/tap \u0026\u0026 brew install sciclaw-dev\n```\n\n`sciclaw-dev` tracks development branch releases. If stable `sciclaw` is already installed, uninstall it first to avoid binary name collisions.\n\nmacOS only:\n```bash\nbrew install --cask quarto\n```\n\n### Download a binary\n\nPre-compiled binaries for macOS (arm64), Linux (amd64, arm64, riscv64), and Windows (amd64/WSL) are on the [releases page](https://github.com/drpedapati/sciclaw/releases).\n\n### From source\n\n```bash\ngit clone https://github.com/drpedapati/sciclaw.git\ncd sciclaw\nmake deps \u0026\u0026 make install\n```\n\nHomebrew pulls companion tools automatically (ImageMagick, IRL, ripgrep, docx-review, xlsx-review, pptx-review, pubmed-cli). For binary/source installs, run `sciclaw doctor` for hints. VM/bootstrap provisioning uses `deploy/toolchain.env` and installs the same core review companions.\n\nAfter any install method, initialize once:\n```bash\n# Recommended: interactive app with first-run setup wizard\nsciclaw app\n\n# CLI alternative (headless/non-TUI)\nsciclaw onboard\n```\n\n## Quick Start\n\n**1. Initialize** — choose one:\n\n```bash\n# Recommended: launches the app and starts first-run setup\nsciclaw app\n\n# CLI alternative (headless/non-TUI)\nsciclaw onboard\n```\n\n**2. Authenticate** with your AI provider:\n\n```bash\nsciclaw auth login --provider openai     # OAuth device code — works with your ChatGPT account\nsciclaw auth login --provider anthropic  # Token paste\n\n# Optional: import from 1Password item JSON (requires OP_SERVICE_ACCOUNT_TOKEN)\nexport OP_SERVICE_ACCOUNT_TOKEN=\"ops_...\"\nsciclaw auth import-op --provider openai --item \"OpenAI Credentials\"\nsciclaw auth import-op --provider anthropic --item \"Anthropic Token\" --vault \"AI\" --auth-method token\n```\n\n**3. Connect a chat app** and start messaging:\n\n```bash\nsciclaw channels setup telegram\nsciclaw service install \u0026\u0026 sciclaw service start\n```\n\nSee [Authentication docs](https://sciclaw.dev/docs.html#authentication) for all providers. See [Chat Channels](#chat-channels) below for Telegram and Discord setup details.\n\n## Security\n\nsciClaw's default posture is **local, private, and locked down**. Here's what that means in practice:\n\n- **Runs on your machine.** sciClaw is a program on your computer, not a cloud service. There's no account to create with us, no server to connect to, nothing hosted anywhere.\n- **Your data stays in one folder.** Everything sciClaw produces lives in `~/sciclaw` — a folder on your machine that you own and control. You can open it, back it up, or delete it anytime.\n- **Nothing is exposed to the internet.** sciClaw doesn't open any ports or listen for incoming connections. It reaches out only when you send a message, and only to the AI provider you chose (OpenAI, Anthropic, etc.) and any tools you explicitly enable (like PubMed).\n- **Messages go through your private bot.** When you chat via Telegram or Discord, messages travel through a bot that only you control. Nobody else can talk to it unless you explicitly allow them.\n- **No telemetry, no analytics, no tracking.** sciClaw sends nothing back to us. No usage data, no error reports, no phone-home behavior. We don't know you're running it.\n- **API keys stay local.** Your credentials are stored in a config file on your machine (`~/.picoclaw/config.json`). They're never transmitted to anyone except the provider they belong to.\n- **Skills are validated before install.** Every skill goes through size limits, binary rejection, frontmatter validation, and SHA-256 provenance logging. Catalog fetches use pinned commit refs for supply-chain hardening.\n\nFor the full security model, see [Security](https://sciclaw.dev/security.html).\n\n## Providers\n\nsciClaw auto-detects the provider from the model name. Set credentials via the onboard wizard or `sciclaw auth login`.\n\n| Provider | Models | Auth |\n|----------|--------|------|\n| **OpenAI** | gpt-5.5, gpt-5.2 (primary), gpt-5.2-chat-latest, gpt-5.2-pro | API key or device-code OAuth |\n| **Anthropic** | claude-sonnet-4.6, claude-opus-4-6, claude-haiku-4-5-20251001 | API key, token paste, or Claude.ai oat-token bridge |\n| **Gemini** | gemini-2.5-pro, gemini-2.5-flash | API key |\n| **OpenRouter** | All models via `openrouter/` prefix | API key |\n| **DeepSeek** | deepseek-chat, deepseek-reasoner | API key |\n| **Groq** | Fast inference + Whisper voice transcription | API key |\n| **Zhipu** | GLM models | API key |\n\n\u003e Groq provides free voice transcription via Whisper. When configured, Telegram voice messages are automatically transcribed.\n\n## Built-in Skills\n\nBundled skills include:\n\n### Research \u0026 Literature\n- **scientific-writing** — Manuscript drafting with claim-evidence alignment\n- **pubmed-cli** — PubMed search, article fetch, citation graphs, MeSH lookup ([CLI tool](https://github.com/drpedapati/pubmed-cli))\n- **biorxiv-database** — bioRxiv/medRxiv preprint surveillance\n\n### Authoring \u0026 Visualization\n- **quarto-authoring** — Loop-driven `.qmd` authoring and rendering\n- **pandoc-docx** — Clean `.docx` manuscript generation from Markdown with NIH template auto-apply\n- **imagemagick** — Reproducible image preprocessing (resize, crop, convert, DPI normalization) via `magick`\n- **beautiful-mermaid** — Publication-grade Mermaid diagrams\n- **explainer-site** — Technical, single-page \"How X Works\" explainer site generation\n\n### Evidence \u0026 Provenance\n- **experiment-provenance** — Reproducible experiment metadata capture\n- **benchmark-logging** — Benchmark records with acceptance criteria\n\n### Office \u0026 Documents\n- **docx-review** — Word tracked-change review, comments, semantic diff, and template population (`--create`, v1.3.0+) ([CLI tool](https://github.com/drpedapati/docx-review))\n- For clean first-draft Word output, use `pandoc ... -o file.docx`; sciClaw injects `--defaults \u003cgenerated-file\u003e` at runtime to apply a bundled NIH reference template (no global `~/.pandoc/defaults.yaml` required).\n- **acroform-fill** — Fill structured PDF/AcroForm fields safely from typed inputs\n- **pptx** — PowerPoint creation and editing\n- **pdf** — PDF creation, merging, splitting, and extraction\n- **xlsx** — Spreadsheet creation, analysis, and conversion\n\n### Polish\n- **humanize-text** — Final-pass language polishing for natural tone\n\n### Optional\n- **phi-cleaner** — Clinical text de-identification for PHI-safe sharing (`brew install drpedapati/tools/phi-cleaner`)\n\nAdditional skills: [skills catalog](https://github.com/drpedapati/sciclaw-skills) — install with `sciclaw skills install drpedapati/sciclaw-skills/\u003cname\u003e`\n\n## Chat Channels\n\nTelegram and Discord are the recommended way to interact with sciClaw. You message it from the app you already have open.\nWhen the agent generates deliverables (for example `.docx`), it can now send real file attachments back through Discord/Telegram via the `message` tool.\n\nDiscord-specific features on current `main`/dev builds:\n- background jobs for long-running requests, with queue-aware progress cards\n- `/btw` slash command for read-only side questions in the same workspace\n- `/skill` slash command with workspace-aware skill autocomplete\n- `/theme` slash command to pick Clear, Formal, or Brief response styles (persists per user)\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eTelegram setup\u003c/strong\u003e (easiest)\u003c/summary\u003e\n\n1. Open Telegram, search `@BotFather`, send `/newbot`, copy the token\n2. Run `sciclaw channels setup telegram` (pairs your account and writes config)\n3. Start the gateway: `sciclaw service install \u0026\u0026 sciclaw service start`\n\nManual config (advanced) in `~/.picoclaw/config.json`:\n\n```json\n{\n  \"channels\": {\n    \"telegram\": {\n      \"enabled\": true,\n      \"token\": \"YOUR_BOT_TOKEN\",\n      \"allow_from\": [\"YOUR_USER_ID\"]\n    }\n  }\n}\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003eDiscord setup\u003c/strong\u003e\u003c/summary\u003e\n\n1. Create app at [discord.com/developers](https://discord.com/developers/applications)\n2. Enable **MESSAGE CONTENT INTENT** in Bot settings\n3. Copy bot token, get your User ID (Developer Mode → right-click → Copy User ID)\n4. Run `sciclaw channels setup discord` or add to config manually\n5. Generate invite URL (scopes: `bot`; permissions: Send Messages, Read Message History)\n6. Start the gateway: `sciclaw service install \u0026\u0026 sciclaw service start`\n\n\u003c/details\u003e\n\n**Background service** (recommended — keeps sciClaw running):\n```bash\nsciclaw service install    # register with launchd (macOS) or systemd (Linux)\nsciclaw service start\nsciclaw service status     # check it's running\n```\n\nFor long-running Discord work, sciClaw now keeps the channel responsive:\n- one main job runs per workspace\n- additional main jobs queue instead of being silently downgraded\n- `/btw` stays read-only and does not mutate the workspace\n\nPlatform notes:\n- **macOS**: per-user `launchd` (`~/Library/LaunchAgents/io.sciclaw.gateway.plist`)\n- **Linux**: `systemd --user` (`~/.config/systemd/user/sciclaw-gateway.service`)\n- **WSL**: service mode works when systemd is enabled; otherwise `sciclaw gateway` in a terminal\n\n## Collaborative Routing (Channel -\u003e Workspace)\n\nGive each project its own chat room. Routing maps a Discord or Telegram channel to a specific data folder so the agent only sees that project's files — while still having access to your shared personality, skills, and memory from `~/sciclaw`.\n\n**Mention to activate.** In routed channels the bot stays quiet unless someone `@mention`s it, so collaborators can talk freely without triggering responses. DMs always work without a mention.\n\nExample:\n\n```bash\nsciclaw routing add \\\n  --channel discord \\\n  --chat-id 123456789012345678 \\\n  --workspace /absolute/path/to/project-a \\\n  --allow 987654321098765432,123456789012345678 \\\n  --label project-a\n\nsciclaw routing enable\nsciclaw routing validate\nsciclaw routing reload\n```\n\nTo let the bot respond to every message (no `@mention` needed), add `--no-mention`:\n\n```bash\nsciclaw routing add \\\n  --channel discord \\\n  --chat-id 123456789012345678 \\\n  --workspace /absolute/path/to/project-a \\\n  --allow 987654321098765432 \\\n  --no-mention\n```\n\nUseful operations:\n- `sciclaw routing status`\n- `sciclaw routing list`\n- `sciclaw routing explain --channel \u003cchannel\u003e --chat-id \u003cid\u003e --sender \u003cid\u003e [--mention] [--dm]`\n- `sciclaw routing set-users --channel \u003cchannel\u003e --chat-id \u003cid\u003e --allow \u003cid1,id2\u003e`\n- `sciclaw routing remove --channel \u003cchannel\u003e --chat-id \u003cid\u003e`\n- `sciclaw routing export --out routing.json` / `sciclaw routing import --in routing.json [--replace]`\n\nSession isolation is namespaced as `\u003cchannel\u003e:\u003cchat_id\u003e@\u003cworkspace_hash\u003e` to prevent cross-workspace context bleed. Each routed workspace gets its own sessions, memory, and state, but inherits your personality files (`AGENTS.md`, `SOUL.md`, etc.) and skills from the shared workspace (`~/sciclaw`).\n\n## IRL Integration\n\nsciClaw integrates with [IRL](https://github.com/drpedapati/irl-template) (Idempotent Research Loop) for project lifecycle management. IRL is installed automatically as a Homebrew dependency.\n\nThe agent manages projects through natural conversation:\n\n```bash\nsciclaw agent -m \"Create a new project for ERP correlation analysis\"\nsciclaw agent -m \"What projects do I have?\"\n```\n\nEvery IRL command is recorded in `~/sciclaw/irl/commands/` for auditability.\n\n## Workspace Layout\n\n```\n~/sciclaw/\n├── sessions/          # Conversation history\n├── memory/            # Long-term memory (MEMORY.md)\n├── state/             # Persistent state\n├── cron/              # Scheduled jobs\n├── skills/            # Installed skills\n├── hooks/             # Hook audit log (JSONL)\n├── irl/commands/      # IRL command audit records\n├── AGENTS.md          # Agent behavior guide\n├── HOOKS.md           # Hook policy (plain-language)\n├── IDENTITY.md        # sciClaw identity\n├── SOUL.md            # Agent values \u0026 guardrails\n├── TOOLS.md           # Tool descriptions\n└── USER.md            # User preferences\n```\n\n## Docker\n\n```bash\ngit clone https://github.com/drpedapati/sciclaw.git \u0026\u0026 cd sciclaw\ncp config/config.example.json config/config.json   # edit with your credentials\ndocker compose --profile gateway up -d              # gateway mode\ndocker compose run --rm sciclaw-agent -m \"Hello\"    # one-shot\n```\n\nThe Docker image is a full runtime and includes:\n`python3`, `uv`, `ripgrep`, `imagemagick`, `pandoc`, `quarto`, `docx-review`, `xlsx-review`, `pptx-review`, `pubmed-cli`, and `irl`.\n\n## Troubleshooting\n\nRun `sciclaw doctor` to diagnose issues — it checks config, auth, tools, skills, gateway, and service health.\n\n```bash\nsciclaw doctor            # human-readable report\nsciclaw doctor --fix      # auto-fix common issues\n```\n\n\u003cdetails\u003e\n\u003csummary\u003eCommon issues\u003c/summary\u003e\n\n**\"no credentials for openai/anthropic\"**\n```bash\nsciclaw auth login --provider openai\n```\n\n**Telegram \"Conflict: terminated by other getUpdates\"** — only one gateway instance can run at a time:\n```bash\nsciclaw service restart\n```\n\n**Web search \"API configuration problem\"** — get a free key at [brave.com/search/api](https://brave.com/search/api) and add to config under `tools.web.search.api_key`.\n\n\u003c/details\u003e\n\n## Updating\n\n```bash\nbrew upgrade sciclaw     # update the binary\nsciclaw onboard          # refresh skills to latest\nsciclaw doctor           # verify everything\n```\n\n## Release Notes\n\nThe old curated patch ledger was removed because it kept drifting behind the codebase.\n\nCurrent sources of truth:\n- GitHub releases: \u003chttps://github.com/drpedapati/sciclaw/releases\u003e\n- local history: `git log --oneline v0.2.3..HEAD`\n- current binary: `sciclaw --version`\n\n\u003cdetails\u003e\n\u003csummary\u003eCLI reference\u003c/summary\u003e\n\n| Command | Description |\n|---------|-------------|\n| `sciclaw app` | Open the graphical dashboard (alias: `tui`) |\n| `sciclaw onboard` | Initialize config, workspace, and baseline skills |\n| `sciclaw agent -m \"...\"` | One-shot message |\n| `sciclaw agent` | Interactive chat |\n| `sciclaw agent --model \u003cm\u003e` | Override model |\n| `sciclaw agent --effort \u003clevel\u003e` | Set reasoning effort (`none` through `xhigh`) |\n| `sciclaw models list` | Show current model and providers |\n| `sciclaw models set \u003cmodel\u003e` | Change default model |\n| `sciclaw models effort \u003clevel\u003e` | Change default effort |\n| `sciclaw status` | System status |\n| `sciclaw doctor` | Verify deployment |\n| `sciclaw doctor --fix` | Auto-fix common issues |\n| `sciclaw gateway` | Start chat gateway |\n| `sciclaw service install\\|start\\|stop\\|restart\\|logs\\|uninstall` | Manage background service |\n| `sciclaw channels setup \u003cchannel\u003e` | Configure a chat channel |\n| `sciclaw auth login\\|logout\\|status\\|import-op` | Manage credentials |\n| `sciclaw skills list\\|install` | Manage skills |\n| `sciclaw web` | Open the web management UI (routing, system config) |\n| `sciclaw prompt inspect --session \u003ckey\u003e` | Token/turn breakdown of a session's prompt |\n| `sciclaw cron list\\|add` | Manage scheduled jobs |\n\n\u003c/details\u003e\n\n### ctxclaw\n\n`ctxclaw` is a standalone context-window optimizer installed automatically with sciClaw. It sits between the agent runtime and the model, compressing stale history to reclaim tokens in long-running sessions. Use `sciclaw prompt inspect` to see where tokens are going before optimizing. See [docs](https://sciclaw.dev/docs.html#ctxclaw) for details.\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n\nsciClaw is a fork of [PicoClaw](https://github.com/sipeed/picoclaw) by Sipeed, which is based on [nanobot](https://github.com/HKUDS/nanobot) by HKUDS.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdrpedapati%2Fsciclaw","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdrpedapati%2Fsciclaw","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdrpedapati%2Fsciclaw/lists"}