Package Exports
- opencode-orchestrator
Readme
β‘ Quick Start
π‘ Tip: Updated daily. Run this command everyday to stay up to date.
npm install -g opencode-orchestratorIn an OpenCode environment:
/task "Implement"Overview
OpenCode Orchestrator is a Distributed Cognitive Architecture designed for high-precision software engineering. It operates on a strict "Verify, then Trust" philosophy, distinguishing itself from simple stochastic chatbots by enforcing rigorous architectural standards.
The system is a testament to the operational paradox: Complexity is easy; Simplicity is hard.
While the user interaction remains elegantly minimal, the internal architecture encapsulates a rigorous alignment of microscopic state management (Rust atoms) and macroscopic strategic planning (Agent Topology). Every component reflects a deep design philosophy aimed at abstracting chaos into order.
Building this system reaffirmed a timeless engineering truth: "Simple is Best" is the ultimate complexity to conquer. This engine is our answer to that challengeβhiding the intricate dynamics of Autonomous Agentic Collaboration behind a seamless, user-friendly veil.
This philosophy extends to efficiency. We achieved Zero-Configuration usability while rigorously optimizing for performanceβdelivering higher quality outcomes than alternatives while saving ~40% of tokens. By maximizing the potential of cost-effective models like GLM-4.7, we prove that superior engineeringβnot just raw model sizeβis the key to autonomous performance.
π Workflow
[ User Task Input ]
β
βββββββββββββΌββββββββββββ ββββββββββββββββββββββββββββββββββββββββββ
β π«‘ COMMANDER (Hub) β (Orchestration) β
βββββββββββββ¬ββββββββββββ β
β β
βββββββββββββΌββββββββββββ β
β ποΈ PLANNER (Map) β (Create TODO.md) β
βββββββββββββ¬ββββββββββββ β
β β
ββββββββββββββββββββΌβββββββββββββββββββ β
β β‘ COMMANDER: Parallel Spawning β β
ββββββββ¬ββββββββββββ¬ββββββββββββ¬βββββββ β
β β β β
ββββββββΌββββ βββββββΌβββββ ββββββΌββββββ β
β π¨ WORKERβ β π¨ WORKERβ β π¨ WORKERβ β
ββββββββ¬ββββ βββββββ¬βββββ ββββββ¬ββββββ β
β β β β
ββββββββΌββββββββββββΌββββββββββββΌβββββββ β
β π COMMANDER: Parallel Reviewers β β
ββββββββ€ββββββββββββ€ββββββββββββ€βββββββ β
β β β β
ββββββββΌββββ βββββββΌβββββ ββββββΌββββββ β
βπREVIEWERβ βπREVIEWERβ βπREVIEWERβ β
ββββββββ¬ββββ βββββββ¬βββββ ββββββ¬ββββββ β
β β β β
ββΌββββββββββββΌββββββββββββΌβ β
β π¦ SYNC BARRIER β β
ββββββββββββββ€βββββββββββββ β
β β
βββββββββββββΌββββββββββββ β
β π VERIFICATION β (Checklist Gate) β
β βββββββββββββββββββ β β
β β [x] Build Pass β β β
β β [x] Tests Pass β β β
β β [x] No Errors β β β
β βββββββββββββββββββ β β
βββββββββββββ¬ββββββββββββ β
β β
__________βΌ_________ β
β± β² NO (Loop / Auto-Correction) β
β± β
Checklist 100%? β² βββββββββββββββββββββββββββββββββββββββββββ
β² π‘οΈ Sync Issues 0? β±
β²____________________β±
β YES
β
[ ποΈ MISSION SEALED ]
β
βββββββββββββΌββββββββββββ
β π OS Notification β
β π΅ Success Sound β
βββββββββββββββββββββββββπ§ Cognitive Architecture & Key Strengths
π Adaptive Context Gating (EMA-based)
We combat "Context Drift" using a mechanism derived from Exponential Moving Average (EMA) algorithms. Irrelevant conversation noise follows a rapid decay curve, while critical architectural decisions are reinforced into Stable Core Memory. This functions as an Attention Sink, allowing agents to work indefinitely without Catastrophic Forgetting.
𧬠BDI (Belief-Desire-Intention) Collaboration
The system implements a variant of the BDI Software Agent Model:
- Belief (Context): Shared state & file system reality.
- Desire (Mission): The user's goal (e.g., "Fix this bug").
- Intention (Plan): The
TODO.mdroadmap execution. Agents do not merely "chat"; they collaborate to align their Beliefs with Desires through strictly executed Intentions, mirroring human engineering squads.
βοΈ Neuro-Symbolic Hybrid Engine
Pure LLM approaches are stochastic. We bind them with a Neuro-Symbolic Architecture that anchors probabilistic reasoning to the deterministic precision of Rust-based AST/LSP Tools. This ensures every generated token is grounded in rigorous syntax analysis, delivering high performance with minimal resource overhead.
β‘ Dynamic Fork-Join Parallelism with Backpressure
The engine features an Intelligent Load-Balancing System that fluidly switches between synchronous barriers and asynchronous Fork-Join patterns. It monitors System Backpressure to dynamically adjust concurrency slots in real-time (Adaptive Throttling), maximizing throughput on high-end hardware while maintaining stability on constrained environments.
π― Iterative Rejection Sampling (Zero-Shot Defense)
We employ a Rejection Sampling Loop driven by the Reviewer Agent (Reward Model). Through the Metric-based Strict Verification Protocol (MSVP), code paths that fail execution tests are pruned. The system iterates until the solution converges on a mathematically correct state (0% Error Rate), rejecting any solution that lacks evidence.
π§© Externalized Chain-of-Thought (CoT)
The Planner's TODO.md serves as an Externalized Working Memory (Scratchpad). This persistent Symbolic Chain-of-Thought decouples detailed planning from the LLM's immediate context window, enabling the orchestration of massive, multi-step engineering tasks without logical degradation.
β‘ Agents
| Agent | Role |
|---|---|
| Commander | Orchestrates the mission, manages parallel threads and sync barriers |
| Planner | Architecture architect. Breaks downtasks into strictly defined steps |
| Worker | The builder. Writes code and corresponding unit tests |
| Reviewer | The gatekeeper. Rejects any code that doesn't pass execution verification |
Developer's Note
Architectural Verification Report β
π License
MIT License. See LICENSE for details.