by sergezuber · MCP Server · ★ 83
A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every green run leaves a receipt anyone can replay. Built for one small model on one machine (LM Studio, MLX) or any OpenAI-compatible endpoint. No telemetry. macOS · Linux · Windows.
| Stars | 83 |
| Forks | 0 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 33.3/100 |
| Last Updated | 2026-09-22 |
| Created | 2026-07-04 |
| Platforms | mcp, node |
| Est. Tokens | ~766k |
These tools work well together with FABULA-LLM-5 for enhanced workflows:
Explore other popular mcp server tools:
FABULA-LLM-5 is A local-first coding agent that doesn't take "done" on faith: the engine keeps the run going until the project's own tests pass, and every green run leaves a receipt anyone can replay. Built for one s. It is categorized as a MCP Server with 83 GitHub stars.
FABULA-LLM-5 is primarily written in TypeScript. It covers topics such as agent-harness, ai-agents, ai-coding-assistant.
You can find installation instructions and usage details in the FABULA-LLM-5 GitHub repository at github.com/sergezuber/FABULA-LLM-5. The project has 83 stars and 0 forks, indicating an active community.
FABULA-LLM-5 is released under the MIT license, making it free to use and modify according to the license terms.