# Ai Orchestrator > Portable multi-agent AI developer setup for Claude Code + Ollama. Role-based local LLM orchestration via Bash — plan, code, review, commit. Zero Dependency. Works with any language stack. - **Type:** MCP server - **Install:** `agentstack add mcp-mybono-ai-orchestrator` - **Verified:** Pending review - **Seller:** [Mybono](https://agentstack.voostack.com/s/mybono) - **Installs:** 0 - **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml) - **Latest version:** 0.1.0 - **License:** MIT - **Upstream author:** [Mybono](https://github.com/Mybono) - **Source:** https://github.com/Mybono/ai-orchestrator ## Install ```sh agentstack add mcp-mybono-ai-orchestrator ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About [](https://github.com/Mybono/ai-orchestrator/actions/workflows/ci.yml) [](https://opensource.org/licenses/MIT) **README** · [Architecture](documentation/ARCHITECTURE.md) · [Agents](documentation/AGENTS.md) · [Skills & Commands](documentation/SKILLS.md) · [Plugins](documentation/PLUGINS.md) --- TypeScript + Bash orchestration that runs AI agents — Ollama for code generation, Claude for planning and triage — in parallel, in dependency order. ## How it works `/implement` triggers a multi-step pipeline. Claude handles triage and planning; the TypeScript orchestrator runs Ollama agents in dependency order; Claude applies the generated output. ```text Step 0 Triage Claude reads graph.json (BFS depth=2), writes triage_ts.md Step 1 Plan Parallel Claude planners write task_context_.md Step 1.5 Orchestrate npm start runs Ollama agents in dependency order, writes ollama_output_.md Step 2 Code Parallel Claude coders apply ollama_output_.md, write coder_output_.md Step 2.5 Pre-review Standards compliance check Step 3 Build npx tsc --noEmit Step 4 Review Fast review per file; deep review for flagged files Step 5 Fix loop Max 3 rounds, circuit breaker on repeat errors Step 6 Finalize git diff + track savings ``` `scripts/run_pipeline.sh` wraps steps 1–3 into a single non-interactive script. Pass a task description and it runs triage, parallel planning, and the TS orchestrator in sequence without any Claude interaction required. Agents communicate through files in `.claude/context/`. Each step reads file paths from the previous step, not the full content. ## Self-learning loop After every pipeline run the orchestrator records what happened and uses it to improve future reviews automatically. ```text Pipeline run └─► capture-outcome.sh ──► knowledge/outcomes.jsonl │ (task, verdict, reviewer_issues, model, duration) │ ├─► embed-outcomes.sh ──► knowledge/embeddings.jsonl │ (mxbai-embed-large via Ollama, runs in background) │ └─► learn.sh --apply ──► skills/discovered/-.md (auto-triggered every 10 outcomes) ``` | Script | What it does | |---|---| | `capture-outcome.sh` | Appends one JSON record per run: task, verdict, files changed, reviewer issues, model, duration | | `embed-outcomes.sh` | Generates Ollama vector embeddings for each outcome; skips already-embedded records | | `semantic-search.sh` | Cosine-similarity search over `embeddings.jsonl`; returns top-k similar past outcomes | | `learn.sh` | Finds recurring reviewer issues (≥ 3 occurrences), calls Ollama reviewer to draft a skill amendment, writes it to `skills/discovered/` | Every 10 captured outcomes `learn.sh --apply` fires automatically (background, no blocking). Discovered amendments land in `skills/discovered/` and are picked up by the reviewer on the next run. Run manually: ```bash # Dry-run: print proposed amendments without writing files bash scripts/learn.sh # Apply: write amendments to skills/discovered/ bash scripts/learn.sh --apply # Query: find issues similar to a specific task description bash scripts/learn.sh --query "add authentication middleware" # Semantic search standalone bash scripts/semantic-search.sh --query "TypeScript type errors" --top-k 3 ``` ## Source layout ```text src/ types/index.ts AgentDomain, KNOWN_DOMAINS, Role, AgentTask, AgentResult (done|skipped|failed|blocked), TriageResult agents/ AgentRunner.ts Wraps call_ollama.sh via spawn; 5 min timeout; 10 MB output limit TriageAgent.ts BFS depth=2 on graph.json; writes triage_ts.md; CLI via import.meta.url core/ DependencyGraph.ts Kahn topological sort; duplicate domain detection Orchestrator.ts Reads task_context_.md; circuit breaker for failed deps; reviews ollama_output_.md after all domains complete BuildChecker.ts Runs npx tsc --noEmit; returns pass/fail with stderr DiffCompressor.ts Strips lock files, collapses blanks, truncates long hunks FileWriter.ts Parses %%FILE...%%ENDFILE blocks from Ollama output; writes to disk TriageRouter.ts Reads triage_ts.md and extracts the chosen TriageRoute cli/ commit.ts npm run ao-commit — calls local-commit.sh via spawn review.ts npm run ao-review — runs reviewer agent on current diff stats.ts npm run ao-stats — prints token savings summary update.ts npm run ao-update — pulls latest orchestrator version mcp/ server.ts MCP HTTP server (default port 3456); exposes get_stats, triage_task, and run_ollama tools to Claude index.ts CLI entry point ``` ## Domain dependencies | Domain | Depends on | |--------|------------| | `coder` | (none) | | `unit-tester` | `coder` | | `doc-writer` | `coder` | | `devops` | `coder`, `unit-tester`, `doc-writer` | Domains within the same dependency level run concurrently. If a domain fails, its dependents are marked `blocked` and skipped. ## Requirements - Node.js 20+ with `tsx` - [Claude Code](https://claude.ai/code) CLI - [Ollama](https://ollama.com) installed and running - `jq` - Python 3 with `graphify` package (optional, for knowledge graph updates) ## Installation ```bash git clone https://github.com/Mybono/ai-orchestrator ~/Projects/ai-orchestrator cd ~/Projects/ai-orchestrator ./scripts/install.sh ``` Or with curl: ```bash curl -sSL https://raw.githubusercontent.com/Mybono/ai-orchestrator/main/scripts/install.sh | bash ``` `install.sh` creates symlinks from `~/.claude/` into the repo. A `git pull` in the repo directory updates all tooling immediately. ## Configuration Model routing is controlled by `llm-config.json` in the repo root: ```json { "models": { "coder": "qwen3:32b-q4_K_M", "reviewer": "qwen3:32b-q4_K_M", "pre-reviewer": "qwen3:8b", "debugger": "qwen3:32b-q4_K_M", "devops": "qwen3:8b", "quick-coder": "qwen3:8b", "commit": "qwen2.5-coder:7b", "triage": "qwen3:8b", "embedding": "mxbai-embed-large" }, "free_api_url": "http://localhost:3001/v1/chat/completions", "free_api": { "planner": "qwen/qwen3-32b", "coder": "qwen3-coder-next", "reviewer": "auto", "pre-reviewer": "auto", "debugger": "qwen3-coder-next", "devops": "auto", "quick-coder": "qwen3-coder-next", "commit": "auto", "triage": "auto" }, "cerebras_api": { "coder": "gpt-oss-120b", "reviewer": "gpt-oss-120b", "pre-reviewer": "gpt-oss-120b", "debugger": "gpt-oss-120b", "devops": "gpt-oss-120b", "quick-coder": "gpt-oss-120b", "commit": "gpt-oss-120b", "triage": "gpt-oss-120b" }, "fallback": { "coder": "claude-sonnet-4-6", "reviewer": "claude-sonnet-4-6", "pre-reviewer": "claude-haiku-4-5-20251001", "debugger": "claude-sonnet-4-6", "devops": "claude-haiku-4-5-20251001", "quick-coder": "claude-haiku-4-5-20251001", "commit": "claude-haiku-4-5-20251001", "triage": "claude-haiku-4-5-20251001", "embedding": "" }, "cloud_first_roles": ["planner", "reviewer", "debugger"] } ``` Routing follows a 4-tier provider chain. Roles listed in `cloud_first_roles` (`planner`, `reviewer`, `debugger`) try Cerebras first, then FreeLLM, then Ollama, then Claude. All other roles start with Ollama, then fall through FreeLLM, Cerebras, and finally Claude. Changing a model name takes effect immediately — no restart needed. See [Architecture](documentation/ARCHITECTURE.md#model-configuration) for details. ## Development ```bash npm run build # compile TypeScript npm run typecheck # tsc --noEmit, no output files npm start "coder,unit-tester" # run TS orchestrator for given domains npx tsx src/agents/TriageAgent.ts "" # run triage standalone npm run ao-commit # generate commit message via Ollama and commit npm run ao-review # review current diff with reviewer agent npm run ao-stats # print token savings (day/week/month) npm run ao-update # pull latest orchestrator version npm run ao-mcp # start MCP server on port 3456 bash scripts/run_pipeline.sh "" # run full pipeline autonomously ``` ## License MIT --- **README** · [Architecture](documentation/ARCHITECTURE.md) · [Agents](documentation/AGENTS.md) · [Skills & Commands](documentation/SKILLS.md) · [Plugins](documentation/PLUGINS.md) ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [Mybono](https://github.com/Mybono) - **Source:** [Mybono/ai-orchestrator](https://github.com/Mybono/ai-orchestrator) - **License:** MIT Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** yes - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: flagged — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-mybono-ai-orchestrator - Seller: https://agentstack.voostack.com/s/mybono - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.