-
Notifications
You must be signed in to change notification settings - Fork 2
Home
lacausecrypto edited this page Apr 9, 2026
·
10 revisions
Welcome to the OCC documentation. OCC is an open-source YAML-first LLM orchestrator — define multi-step chains in YAML, execute them with automatic parallel processing, 30 pre-tools at zero token cost, and access everything via MCP, REST API, or the Chimera React dashboard.
3243 tests (111 files), 102 REST endpoints, 28 MCP tools, 6 LLM providers, setup check modal.
- Getting Started — Install, configure, run your first chain in 5 minutes
-
Configuration — Environment variables,
.mcp.json, Docker, deployment
- Chain Format — Complete YAML reference for chain definitions
- Step Types — All 11 step types explained with examples
- Pre-Tools — 29 pre-tool types (web search, API calls, MCP, bash, state, vector, etc.)
- Pipelines — Chain multiple chains together
- CLI — Command-line interface: run, validate, dry-run, cost estimate (17 commands)
- REST API — 102 HTTP endpoints with request/response examples
- MCP Tools — 28 MCP tools for Claude Code / Claude Desktop
- MCP Client — Consume 10,000+ external MCP servers in chains
- Architecture — 18 modules: executor, queue, storage, linter, MCP client, providers, etc.
- Token Optimization — Minimize cost with caching, transforms, context strategies
- Cookbook — Practical recipes and patterns
- FAQ — Common questions and troubleshooting
| Concept | Description |
|---|---|
| Chain | A YAML file defining a multi-step workflow. Each step is an LLM call, data transform, or control flow. |
| Step | One unit of work in a chain. 11 types: agent, router, evaluator, gate, transform, loop, merge, browser, subchain, debate, webhook. |
| Pipeline | Multiple chains executed in sequence/parallel, with outputs passed between them. |
| Pre-tool | Data injection before a step — 29 types including web search, HTTP fetch, file read, bash, env var, MCP call, vector query, state management, semantic cache. Supports on_error (inject/skip/fail), retry, parallel execution. |
| Variable | Outputs stored as output_var and interpolated into prompts via {variable_name}. Supports {key.subkey} and {key|"fallback"}. |
| Wave | A group of steps with no dependencies between them — they execute in parallel. |
| Gate | A step that pauses execution until a human approves or rejects via the API or dashboard. |
| Queue | Persistent SQLite job queue — if all workers are busy, new executions are queued with priority. |
| Checkpoint | Each step result is saved to SQLite immediately. Crash recovery resumes from last completed step. |
| Execution | A running instance of a chain, with its own ID, status, step results, and SSE stream. |
| Provider | An LLM backend: Claude CLI, OpenRouter, OpenAI, Ollama (local), HuggingFace, or any OpenAI-compatible API. |
| BLOB | The visual canvas — an organic workflow graph builder with conversational AI. |
| Workflow Chat | A chat-based chain builder with agentic actions (run, stop, debug, modify steps). |
| Setup Check | On first launch, a modal verifies all prerequisites (Claude CLI, Ollama, Docker...) with action buttons and auto-refresh. |
| Metric | Value |
|---|---|
| REST endpoints | 102 |
| MCP tools | 28 |
| Pre-tool types | 30 (including image_generate) |
| Step types | 12 (including image_gen) |
| Input types | 9 (string, number, boolean, enum, file, image, json, url, text) |
| LLM providers | 6 (Claude, OpenRouter, OpenAI, Ollama, HuggingFace, Custom) |
| Example chains | 19 (including 3 benchmark chains) |
| Example pipelines | 5 |
| Backend test files | 59 |
| Backend tests | 2344 |
| Frontend test files | 52 |
| Frontend tests | 899 |
| Total tests | 3243 |
| CI platforms | Ubuntu, macOS, Windows ×ばつ Node 20 + 22 |