# 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.

- **URL**: https://www.freshcrate.ai/projects/ai-orchestrator
- **Author**: Mybono
- **Category**: MCP Servers
- **Latest version**: `v1.0.17` (2026-04-19)
- **License**: MIT
- **Source**: https://github.com/Mybono/ai-orchestrator
- **Language**: HTML
- **GitHub**: 92 stars, 15 forks
- **Registry**: github
- **Tags**: `agentic`, `agentic-ai`, `claude-code`, `cli`, `coding-assistant`, `local-llm`, `mcp`, `ollama`, `shell`

## Description

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.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `v1.0.17` | 2026-04-19 | High | ## What's Changed - **Orchestrator**: Implemented file writing for generated code. - **Scripts/Open-PR.sh**: Updated to handle null responses from Ollama. - **Doc-Writer**: Updated markdown linting rules and fixes. - **UI**: Refactored layout for improved usability.  ## Bug Fixes - Fixed an issue with script execution in project root configuration. - Addressed a bug in handling null responses from external services in the open PR script. |
| `v1.0.16` | 2026-04-17 | High | **What's Changed:**  - **AI Orchestrator:** Updated git hooks and watcher settings for better automation. - **TypeScript Refactoring:** Added `Role` type and updated `AgentResult`. - **Orchestrator Updates:** Limited stdout and stderr output sizes, streamlined code updates for efficiency, and improved the orchestrator run method. - **Triage Agent:** Introduced a dynamic domain detection feature in the triage agent. - **TypeScript Integration:** Updated orchestrator logic to handle domain-specif |
| `v1.0.15` | 2026-04-10 | High | ### What's Changed  - **Token Tracking Update**: Claude token tracking has been updated to reflect real counts with fallback mechanisms. - **PR Label Automation**: Automatically add PR labels based on commit prefixes.  ### Bug Fixes  - None noted.  ### Breaking Changes  - None noted. |
| `v1.0.14` | 2026-04-10 | Medium | ## What's Changed  - **Version Bump**: Updated the version to 1.0.14. - **Automated PR Labels**: Implemented automatic addition of PR labels based on commit prefixes, streamlining issue management. - **Token Tracking Update**: Improved token tracking with real counts and added fallback mechanisms for accurate monitoring. - **Changelog Sync**: Automated sync of the changelog after merge to ensure it remains up-to-date.  ## Bug Fixes  - None identified in this release.  ## Enhancements  - Streaml |
| `v1.0.13` | 2026-04-10 | Medium | **What's Changed:** - **Refactored AI Orchestrator:** Updated the handling of git diff for better context processing. - **Updated Architecture:** Improved agent-to-agent communication and streamlined task flow. - **Workflow Enhancements:** Modified the workflow for pre-review and coder steps to enhance efficiency.  **Bug Fixes:** - Synced the changelog after merge. - Updated SVG diagram and package version.  These updates aim to improve overall performance, usability, and reliability of the app |
| `v1.0.12` | 2026-04-10 | Medium | What's Changed: - **Improved GPU VRAM Calculation**: Enhanced scripts for more accurate GPU VRAM usage calculation and added a benchmark option. - **Model Version Update**: Updated the model version in `agents/quick-coder.md` to qwen2.5-coder:7b.  Bug Fixes: - **Proactive Linting**: Added shellcheck for proactive linting, which fixed CI failures. - **Trailing Whitespace Removal**: Removed trailing whitespace from `settings.json`.  Refactorings: - Updated benchmarks and configurations in the ai- |
| `v1.0.11` | 2026-04-10 | Medium | ## What's Changed - **Model Update**: The model version for `quick-coder.md` has been updated to `qwen2.5-coder:7b`. - **Performance Enhancements**: Improved GPU VRAM calculation and added a benchmark option in the scripts. - **Benchmark Updates**: Updated benchmarks and configurations in the AI orchestrator to improve performance.  ## Bug Fixes - Fixed inconsistencies in model configurations and documentation within the AI orchestrator.  These updates aim to enhance the functionality, performa |
| `v1.0.10` | 2026-04-10 | Medium | ## What's Changed - **Model Update**: Updated the model version in `agents/quick-coder.md` to qwen2.5-coder:7b. - **Performance Improvements**: Enhanced GPU VRAM calculation and added a benchmark option in `scripts`. - **AI Orchestrator Enhancements**:   - Updated benchmarks and configurations for better performance.   - Fixed model configurations and documentation for consistency.  ## Bug Fixes - Addressed issues with Markdown Review by integrating Ollama.  ## Changelog Sync - Synchronized the |
| `v1.0.9` | 2026-04-09 | Medium | What's Changed: - Updated markdown review script to handle lint errors more gracefully and improve overall flow. - Added proactive markdown review for staged files during the ai-orchestrator process. - Integrated initial support for integration tests and release management in triage.md plugin.  Bug Fixes: - Fixed several auto-fix markdown lint errors. - Improved error handling and added context budget in orchestrator refactoring. - Enhanced security by adding JWT-based API authentication to the |
| `v1.0.7` | 2026-04-09 | Medium | **What's Changed** - Added support for integration tests and improved release management within the orchestrator. - Introduced a new plugin-route for specific tasks to enhance flexibility and route logic refinement. - Implemented initial API authentication using JWT in AI Orchestrator. - Added context budget and enhanced error handling mechanisms. - Updated agent documentation for context-manager, error-coordinator, performance-monitor, and security-auditor. - Integrated an AI-driven CI Debugge |

## Dependency audit

- **Score**: 100/100
- **Total deps**: 3
- **Resolved**: 3
- **Unresolved**: 0
- **License conflicts**: 0
- **Warnings**: 0
- **Scanned**: 2026-05-18

## Citation

- HTML: https://www.freshcrate.ai/projects/ai-orchestrator
- Markdown: https://www.freshcrate.ai/projects/ai-orchestrator.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/ai-orchestrator/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._