Toolbox/Autonomous SWE agents/sergezuber/FABULA-LLM-5

sergezuber/FABULA-LLM-5

The agent harness that makes small local models finish hard tasks — and prove it. Done is enforced by the engine, not the prompt: gates, rewinds, a judge, and a replayable Proof-of-Done receipt on every finished run. Any model in the socket. Local, sovereign, air-gapped-capable. macOS · Linux · Windows.

View on GitHub →
TypeScriptMITagent-harnessai-agentsai-coding-assistantllm-agentlm-studio
Stars
83
Δ 7d
-1
Δ 30d
+21
Age
2 mo
Last push
3d ago
10087746148Jul 17Aug 5Sep 2
90-day star history

Where this sits in the catalog

Alternatives in Autonomous SWE agents

OmO: Drop your tokens. Ultrawork. Done.

68.7k
+1867d
TypeScript
9 mo

Clone any website with one command using AI coding agents

33.8k
+4687d
JavaScript
5 mo

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work inste…

27.0k
+1117d
Elixir
6 mo

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be empl…

20.2k
+477d
Python
2 yrs

"DeepCode: Open Agentic Coding (Agent Harness & Loop Engineering & Multi-Agent Orchestration)"

16.5k
+397d
Python
1 yr

The best way to get AI coding agents to solve hard problems in complex codebases.

11.4k
+677d
TypeScript
2 yrs