Summary
You'd reach for this when you need AI task orchestration that handles the complexity for you. It automatically breaks down requests into subtasks, runs them in parallel where possible, and routes each piece to the most appropriate model across six different LLMs. The self-healing aspect means it can recover from failures and retry with different strategies. Think of it as a smart middleware layer that sits between your application and various language models, deciding how to decompose work, which model handles what, and how to stitch results back together. Useful when you're building agents or workflows that benefit from multi-model strategies without manually coding all the routing and error handling logic.
Fastest browser for AI agents to run web automation tasks, always free.
Download Free life-time →
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →
Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →Tools
Public tool metadata for what this MCP can expose to an agent.
12 tools
initInitialize a new orchestration for a feature. Creates .orchex/active/manifest.yaml with streams.3 params
Initialize a new orchestration for a feature. Creates .orchex/active/manifest.yaml with streams.
Parameters* required
featurestringFeature name (e.g., "user-authentication")
project_dirstringProject directory (defaults to cwd)
streamsobjectMap of stream ID → stream definition
add_streamAdd a new stream to the active orchestration.9 params
Add a new stream to the active orchestration.
Parameters* required
depsarrayStream IDs this depends on
idstringUnique stream ID
namestringHuman-readable stream name
ownsarrayFile paths this stream owns
planstringImplementation plan for the stream
project_dirstringProject directory
readsarrayFile paths this stream needs to read (but does not own)
setuparraySetup commands to run before the stream executes
verifyarrayVerification commands to run after the stream completes
statusGet the current orchestration status and progress.1 params
Get the current orchestration status and progress.
Parameters* required
project_dirstringProject directory
executeRun the orchestration. Each call executes one wave of streams in parallel via LLM API, applies artifacts to the codebase, and runs verification commands. Call repeatedly for each wave, or use auto mode.7 params
Run the orchestration. Each call executes one wave of streams in parallel via LLM API, applies artifacts to the codebase, and runs verification commands. Call repeatedly for each wave, or use auto mode.
Parameters* required
dry_runbooleanPreview without executing (default: false)default: false
iteratebooleanWhen true with mode=auto, re-plan and re-execute if failures remain. Max 3 iterations.default: false
max_iterationsnumberMaximum iterations for iterative mode (default: 3, max: 5).default: 3
modestringauto: execute all waves sequentially. wave: execute one wave and return.one of
auto · wavedefault: wavemodelstringLLM model override (auto-detected based on provider)
project_dirstringProject directory
wavenumberRun a specific wave number (optional)
completeMark a stream as complete, or archive the entire orchestration.3 params
Mark a stream as complete, or archive the entire orchestration.
Parameters* required
archivebooleanArchive the orchestrationdefault: false
project_dirstringProject directory
stream_idstringStream ID to mark complete
recoverRecover streams stuck in in_progress state or failed state. Auto-detects stuck streams and resets them to pending for retry, or skips them.4 params
Recover streams stuck in in_progress state or failed state. Auto-detects stuck streams and resets them to pending for retry, or skips them.
Parameters* required
include_failedbooleanAlso recover failed streams (not just stuck in_progress ones).default: false
modestringretry: reset stuck streams to pending. skip: mark them as skipped.one of
retry · skipdefault: retryproject_dirstringProject directory
stream_idstringSpecific stream ID to recover. If omitted, recovers all stuck streams.
learnParse a planning document and generate stream definitions. Returns proposed streams for review before initialization.6 params
Parse a planning document and generate stream definitions. Returns proposed streams for review before initialization.
Parameters* required
deliverable_levelnumberHeader level for deliverables (2=H2, 3=H3)default: 2
document_contentstringPlan document contents as string. When provided, used instead of reading document_path from disk. Useful for cloud mode where the server cannot access local files.
document_pathstringPath to the markdown planning document
prefixstringOptional prefix for stream IDs
project_dirstringProject directory (for resolving relative paths)
validate_antipatternsbooleanValidate generated streams against anti-patternsdefault: true
init-planGenerate an annotated markdown plan template that teaches users how to structure documents for orchex learn. Creates a starter plan file with inline comments explaining what the learn pipeline parses.3 params
Generate an annotated markdown plan template that teaches users how to structure documents for orchex learn. Creates a starter plan file with inline comments explaining what the learn pipeline parses.
Parameters* required
feature_namestringFeature name for the plan (used in title and example stream IDs)default: my-feature
output_pathstringOutput file path. Defaults to docs/plans/YYYY-MM-DD-<feature>-plan.md
project_dirstringProject directory (defaults to cwd)
autoGenerate a plan from user intent, preview streams, and optionally execute. Flow: gather context → LLM generates plan → learn pipeline → preview → approve → execute → report.6 params
Generate a plan from user intent, preview streams, and optionally execute. Flow: gather context → LLM generates plan → learn pipeline → preview → approve → execute → report.
Parameters* required
approvebooleanIf true, execute immediately after preview. If false (default), return preview only.default: false
approved_streamsarrayStream IDs to approve for execution. Non-listed pending streams will be skipped. Omit this parameter to approve all streams (default behavior).
intentstringWhat you want to build (e.g., "Add user authentication with JWT")
modelstringLLM model override
project_dirstringProject directory (defaults to cwd)
providerstringLLM provider override
reset-learningReset learning data: thresholds, events, patterns, and/or reports.4 params
Reset learning data: thresholds, events, patterns, and/or reports.
Parameters* required
confirmbooleanMust be true to proceed
patterns_onlybooleanOnly reset patternsdefault: false
project_dirstringProject directory
reports_onlybooleanOnly reset reportsdefault: false
rollback-streamRevert file changes made by a specific stream using git.2 params
Revert file changes made by a specific stream using git.
Parameters* required
project_dirstringProject directory
stream_idstringStream ID to rollback
reloadRestart the MCP server to pick up rebuilt code. MCP client will reconnect automatically.
Restart the MCP server to pick up rebuilt code. MCP client will reconnect automatically.
No parameter schema in public metadata yet.
Featured
Fastest browser for AI agents to run web automation tasks, always free.
Download Free life-time →Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →Configuration
ANTHROPIC_API_KEYsecretAnthropic API key — auto-detected from shell env; override only
OPENAI_API_KEYsecretOpenAI API key — auto-detected from shell env; override only
GEMINI_API_KEYsecretGemini API key — auto-detected from shell env; override only
DEEPSEEK_API_KEYsecretDeepSeek API key — auto-detected from shell env; override only
ORCHEX_API_URLOverride cloud API URL (optional, defaults to https://orchex.dev)