Integrations Open-Core
Intutic supports 39 AI agent harnesses out of the box. Run intutic init in your project and the CLI auto-detects which agents are present, then syncs governance rules to each one.
intutic init
# ✔ Detected harnesses:
# ✔ cursor → .cursorrules
# ✔ claude-code → CLAUDE.md
# ✔ antigravity → .gemini/settings.jsonEvery harness connects through the same governance pipeline — proxy interception, SOP evaluation, and real-time enforcement — regardless of the underlying agent.
IDE Extensions
Code editors with built-in AI that read project-level config files.
| Harness | Description | Config File |
|---|---|---|
| Cursor | AI-powered code editor by Anysphere | .cursorrules |
| Windsurf | AI-native code editor by Codeium | .windsurfrules |
| Cline | VS Code extension for autonomous agentic coding | .cline/hooks/hooks.json |
| Roo Code | AI-powered VS Code extension (formerly Roo Clinic) | .roorules |
| Continue | Open-source autopilot for VS Code and JetBrains | .continue/config.json |
CLI Tools
Terminal-based agents that accept proxy environment variables or config files.
| Harness | Description | Config File |
|---|---|---|
| Claude Code | Anthropic's agentic coding tool | CLAUDE.md |
| Aider | AI pair programming CLI | .aider.conf.yml |
| Codex | OpenAI's autonomous coding agent | .env.intutic |
| Antigravity | Google's Gemini AI coding agent | .gemini/settings.json |
| Grok Build | xAI's terminal coding agent | AGENTS.md |
| Muse Code | Meta's beta terminal coding agent (model Muse Spark) | AGENTS.md |
| dsh Preview | DeepSeek's plugin-first ("Cordis") coding agent (developer preview) | cordis.patch.yml (Cordis plugin, not a rules file) |
Agent Frameworks
Autonomous coding agents that run multi-step tasks with tool use.
| Harness | Description | Config File |
|---|---|---|
| LangGraph | LangChain's graph-based agent framework | .env.intutic + SDK gate |
| LangChain | LangChain v1.x agents (AgentMiddleware) | .env.intutic + SDK gate |
| CrewAI | Multi-agent orchestration framework | .env.intutic + SDK gate |
| Google ADK | Google's Agent Development Kit | .env.intutic + SDK gate |
| OpenAI Agents SDK | OpenAI's Python agents SDK | .env.intutic + SDK gate |
| AutoGen | Microsoft's multi-agent conversation framework | .env.intutic + SDK gate |
| AG2 | CrewAI-style fork/continuation of pre-Microsoft AutoGen | .env.intutic + SDK gate |
| Pydantic AI | Pydantic's typed agent framework | .env.intutic + SDK gate |
| smolagents | Hugging Face's code-executing agent framework | .env.intutic + SDK gate |
| Strands Agents | AWS's open-source agent framework (Bedrock AgentCore default) | .env.intutic + SDK gate |
| Mastra | TypeScript agent framework | .env.intutic + SDK gate |
| Vercel AI SDK | Vercel's ai package (v6+) | .env.intutic + SDK gate |
| eve Preview | Vercel's filesystem-first durable backend agent framework | .env.intutic + SDK gate (per-tool/connection approval) |
| AI SDK Harness | Vercel's @ai-sdk/harness — coding-agent harnesses in Vercel Sandbox microVMs | .env.intutic + SDK gate (approval flow; see sandbox caveats) |
| AI SDK Workflow | Vercel's @ai-sdk/workflow — durable workflow agents on the Workflow DevKit | .env.intutic + SDK gate (needsApproval) |
| AWS Bedrock AgentCore | AWS's managed hosting environment for the Runtime module — runs your own agent code (any framework) unchanged | none — delegates to whichever already-supported framework adapter your code uses |
| OpenHands | Open-source AI software developer platform | config.toml |
| Goose | Block's terminal agent and desktop framework | .agents/plugins/ |
| Hermes | NousResearch's skill-based developer agent | .hermes/config.yaml |
| Pi | Inflection AI's developer command-line assistant | .pi/hooks.json |
| OpenClaw | Developer terminal agent | .openclaw/openclaw.json |
Platforms
Web UIs, desktop apps, and collaboration tools that host AI agents.
| Harness | Description | Config File |
|---|---|---|
| n8n | Workflow automation platform | API-based |
| Open WebUI | Web interface for LLMs | .open-webui/ filter |
| Claude Desktop | Anthropic's desktop application | claude_desktop_config.json |
| GitHub Copilot | GitHub's AI pair programmer | .github/copilot-instructions.md |
| Xirp | Spotify's macOS orchestrator for parallel Claude Code/Codex/Gemini CLI sessions, each in its own tmux session + git worktree | none — delegates to the wrapped harness |
| Agentic Orchestrator | DoorDash's open-source (Apache-2.0) desktop app + CLI (agentico) for multi-phase feature workflows across Claude Code/Codex/OpenCode, each in its own git worktree | none — delegates to the wrapped backend (OpenCode has no gate — see notes) |
Server-Side Platform Integrations
Backend platforms that call Intutic directly over HTTP as part of their own contract, rather than being detected and configured by intutic init/intutic connect. No HarnessType enum entry, no CLI harness registration — deployment is a config step against the platform's own settings.
| Platform | Description | Integration point |
|---|---|---|
| QM | YC-backed, OSS multiplayer agent harness (wraps pi/claude/codex/opencode) | securityScreen HTTP contract (qm.config.jsonc) |
| Anthropic Managed Agents | Anthropic-hosted "session" that executes tool calls server-side rather than in your own process | Session-confirmation responder (IntuticSessionConfirmer) answering user.tool_confirmation events |
| AWS Bedrock AgentCore Gateway | Deployed AWS resource that forwards MCP tools/call requests to a target — distinct from the Runtime module above | tools/agentcore-interceptor Lambda calling POST /api/v1/integrations/agentcore/gateway-check |
Single-Agent & Multi-Agent Support
Intutic provides zero-trust governance regardless of your agent architecture:
- Single-Agent Assistants: Governs individual coding tools (Claude Code, Cursor, Windsurf, Aider, Antigravity). Tool calls, file writes, and shell execution are intercepted synchronously before execution.
- Multi-Agent Swarms & Graphs: Governs multi-agent frameworks (LangGraph, CrewAI, AutoGen, OpenHands, OpenClaw, Hermes). Every node's traffic crosses the same proxy under one session ID, so rules see the whole graph's tool history rather than a single node's turn — which is what makes ordering constraints, cycle-breaking and a shared budget ceiling enforceable across nodes. The request context also carries per-node identity —
node_id,agent_role,graph_id,parent_session_id,depth— so rules can target one role or node as well as constrain the graph globally. Identity is client-supplied and unverifiable, so it scopes rules and observability only; authorisation stays bound to the virtual key. See Graph Guardrails.
Because every response byte passes through the proxy before the client sees it, the proxy also enforces the tool deny list on the response path (the response gate, open-core, default-on): a model-emitted tool_calls[] naming a denied tool is withheld before the harness's tool runner ever sees it — harness-agnostic, no client hook required, on both streaming and non-streaming responses (Anthropic, OpenAI chat-completions, and OpenAI Responses wire shapes). It is fail-closed within its scope: inert unless the active role has a non-empty deny list, and within that scope an unparseable non-streaming body is refused rather than forwarded. Two precise limits: on streams it enforces at the tool name level only (arguments arrive as JSON fragments across chunks, so argument-level rules are non-streaming-only), and it cannot see locally-originated tool calls that never traverse the proxy.
Universal Harness Compatibility & SDKs
- Any Custom Harness: Direct any custom agent or LLM client to the local Intutic proxy port (
:4000):bashexport ANTHROPIC_BASE_URL="http://localhost:4000/v1" export OPENAI_BASE_URL="http://localhost:4000/v1" - Zero-Code Proxying: No SDK modification required inside your agent codebase — Intutic operates transparently at the network/proxy layer.
- WASM Policy Rules SDK (
@intutic/wasm-sdk): Compile custom policy rules in AssemblyScript, TypeScript, C, or Rust into hot-path proxy filters. See Custom Filters (WASM Rules Engine).
Additional Integrations
| Integration | Description |
|---|---|
| Standalone Proxy | Route any LLM traffic through your own proxy without a harness adapter — works with any OpenAI-compatible client |
| Kitkat Agent Custom Skill | Pre-built governance skill for agents that support custom skill files (.intutic/SKILL.md) |
How it works
All harnesses share the same integration flow:
┌──────────────┐ ┌─────────────┐ ┌──────────────┐
│ intutic │────▶│ Detect │────▶│ Write │
│ init │ │ harnesses │ │ config │
└──────────────┘ └─────────────┘ └──────┬───────┘
│
┌──────────────┐ ┌─────────────┐ ┌──────▼───────┐
│ Enforce │◀────│ Evaluate │◀────│ intutic │
│ verdict │ │ SOPs │ │ connect │
└──────────────┘ └─────────────┘ └──────────────┘intutic initscans your workspace and detects all harness config files- Governance rules (SOPs) are written into each harness's native config format
intutic connectstarts the proxy and keeps configs in sync as SOPs change (intutic connectneeds a control plane. Without one,intutic startruns the proxy and every harness config written in step 2 still applies.)- Every tool call flows through the proxy for real-time policy evaluation
Each adapter uses atomic writes (write to temp file, then rename) to prevent config corruption during sync.
For the technical details of each config format (markdown, YAML, JSON, TOML, env), see the Integration Overview.