InnoClaw

July 3, 2026 · View on GitHub

InnoClaw Logo

A self-hostable AI research workspace for grounded chat, paper study, scientific skills, and research execution.

English · 简体中文 · 日本語 · Français · Deutsch

InnoClaw turns server-side folders into AI-native workspaces where you can chat over your own files, study papers, and run experiments — all in one place.

Instead of juggling separate tools for literature, notes, code, and automation, you open a folder, sync it, and work: cited answers over real documents, structured paper reviews, reusable scientific skills, and a path from reading to remote execution.

InnoClaw Workflow

Who This Is For

Researchers who read papers, run experiments, and want cited AI answers grounded in their own files
ML / AI engineers who need a workspace for code, data, and agent-assisted execution on remote clusters
Lab teams who want a shared, self-hosted research hub instead of scattered SaaS tools
Self-hosters who want full control over their data, models, and infrastructure

3-Minute Quick Start

Requires Node.js 24+ (package.json is the source of truth). If you use nvm: nvm install && nvm use.

git clone https://github.com/SpectrAI-Initiative/InnoClaw.git
cd InnoClaw
npm install
cp .env.example .env.local          # then edit: set WORKSPACE_ROOTS and at least one API key
mkdir -p ./data
npx drizzle-kit migrate
npm run dev                          # open http://localhost:3000

After the UI opens: Settings → configure a model provider → open a workspace → click Sync → start chatting.

Optional CLI

npm link
innoclaw
innoclaw run --prompt "Summarize the current workspace"

The CLI uses the same local app runtime as the web UI. When auth is enabled, it auto-starts the app, opens the browser login page on localhost, and stores a dedicated CLI session after sign-in. For trusted headless automation, start the app with authentication disabled.

Headless local run mode:

npm run dev:no-auth

Security: InnoClaw includes shell execution and remote job submission capabilities. See SECURITY.md for deployment hardening and trust boundary documentation.

Environment variables, upgrade flow, and advanced setup

Set WORKSPACE_ROOTS in .env.local to one or more absolute paths where your research folders live:

WORKSPACE_ROOTS=/absolute/path/to/workspaces
OPENAI_API_KEY=sk-...

WORKSPACE_ROOTS directories must already exist before startup
npx drizzle-kit migrate creates or upgrades the SQLite schema at ./data/innoclaw.db
If the repo lives on NFS/CIFS or another mount without local file locking, InnoClaw now disables Next's dist-dir lock automatically so npm run dev can start. You should still set DATABASE_URL to a local disk path for SQLite. NEXT_BUILD_DIR, if used, must stay inside the repo (for example .next-local).

Upgrading:

git fetch --tags
git checkout vX.Y.Z      # or: git pull (if tracking main)
npm install
npx drizzle-kit migrate
npm run build

Check CHANGELOG.md before every upgrade. Compare .env.local against .env.example for new variables.

For OS-specific prerequisites and production deployment: see Installation and Deployment.

Docker Deployment

git clone https://github.com/SpectrAI-Initiative/InnoClaw.git && cd InnoClaw
cp .env.production.example .env.production.local   # edit: set API key + WORKSPACE_ROOTS
docker compose up -d                                # open http://localhost:3000

See the full Docker Deployment Guide for volumes, reverse proxy, backups, and upgrades.

Choose Your Path

InnoClaw supports three primary workflows. Pick the one that matches what you need today — you can always explore the others later.

1. Read & Study Papers

Search literature across ArXiv, PubMed, bioRxiv, and Semantic Scholar. Summarize papers, run structured multi-role discussions (moderator, skeptic, librarian, reproducer, scribe), and generate research ideation from what you read.

Start here: open Paper Study in any workspace.

2. Work in a Research Workspace

Open a server folder as a persistent workspace. Chat over your files with RAG-backed citations. Browse, edit, and sync files. Use the agent panel to run multi-step tasks with tool calling. Import reusable scientific skills across domains like drug discovery, genomics, and protein science.

Start here: create a workspace, click Sync, and ask a question.

Generic Kubernetes Job Scheduler: Enable AI agents to define, validate, and execute containerized workloads on Kubernetes clusters with configurable job profiles

2026-06-26

CLI Runtime Support: Interactive command-line interface with REPL, batch operations, and agent integration for terminal-based workflows

Show earlier updates

2026-06-12

Disabled Auth Mode: Run the application without authentication for single-user or development deployments

2026-05-12

Local User Authentication: Added built-in account registration, sign-in, sign-out, and persistent session support.
Admin User Management: Added an admin users page to create accounts and manage roles, access, passwords, and ownership.
CLI Login Handoff: innoclaw now supports interactive terminal mode, one-shot run, JSON batch, and browser-to-CLI session handoff.

2026-04-17

InnoClaw CLI: Run the app, manage workspaces, and create/run/export Deep Research sessions from the terminal
Deep Research Checkpoints: Research now pauses at review points so you can continue, revise, branch, reject, or stop runs
Role Studio: New Deep Research tab to inspect specialist roles and send targeted instructions to the Researcher or workers

2026-04-12

Docker Deployment Support: Self-host InnoClaw with Docker and docker-compose, with guides for setup, volumes, and upgrades
200+ Built-in Skills: Massive expansion of ready-to-use scientific skills across bioinformatics, chemistry, genomics, and physics
Skill Creator Framework: New meta-skill for creating, evaluating, benchmarking, and validating custom skills

2026-04-02

Docker Deployment Support: Added Dockerfile, docker-compose.yml, and full Docker deployment guide for self-hosted production setups
200+ New Built-in Skills: Expanded skill library with bioinformatics, cheminformatics, genomics, physics, and drug discovery pipelines
Skill Creator Framework: New meta-skill with evaluation, benchmarking, and validation tooling for building and testing custom skills

2026-04-01

Text-to-CAD Skill: New agent skill that converts natural language descriptions into 3D CAD models (STL/STEP) using CadQuery, with automatic environment setup
Workspace Image Picker: New dialog UI in the agent panel for browsing and selecting images from the workspace to attach to conversations

2026-03-31

Pasted Image Support: Users can now paste images directly into the chat input for multimodal AI conversations
Deep Research Role Studio: New Role Studio panel lets users configure and manage custom researcher roles in the deep research workflow
Expanded Paper Search Sources: Added BioRxiv, PubMed, and PubChem as searchable paper sources in Paper Study

2026-03-26

Dynamic Model Discovery: Agent panel now auto-fetches available models from each configured AI provider, merging live results with built-in model lists
Per-Model Base URL Routing: Chinese AI providers (shlab, qwen, moonshot, deepseek, minimax, zhipu) now support per-model <PROVIDER>_<MODEL>_BASE_URL env vars for flexible endpoint routing
Runtime Tool-Calling Override: Tool support can now be toggled per provider via <PROVIDER>_TOOLS_ENABLED=true/false without code changes

Feature Snapshot

Feature	What it enables
Workspace Management	Map server folders into persistent AI workspaces
File Browser	Browse, upload, create, edit, preview, and sync files
RAG Chat	Ask grounded questions over indexed files with citations
Paper Study	Search, summarize, and inspect papers from ArXiv, PubMed, bioRxiv, and more
Discussion Mode	Run structured multi-role paper discussions
Research Ideation	Generate new directions and cross-disciplinary ideas
Skills System	Import reusable scientific and workflow skills
Deep Research	AI-driven multi-phase research with workflow graph and role-based execution
Research Execution	Orchestrate remote experiment loops with monitoring and approval gates
Multi-Agent Sessions	Keep separate execution contexts across tabs and projects
Multi-LLM Support	Use OpenAI, Anthropic, Gemini, and compatible endpoints

Architecture

Layer	Role
Workspace	Files, notes, session context, and project state
Knowledge	RAG index over synced files for grounded answers
Paper Workbench	Literature search, summary, discussion, and ideation
Skills	Reusable domain workflows and tool-guided capabilities
Execution	Remote jobs, experiment loops, and result collection