AI/TLDR

Antoine Zambelli · 2026-05-19 · notable

Forge — Open-Source Guardrails Lift a Self-Hosted 8B Local Model From 53% to 99% on Multi-Step Agentic Tool-Calling Workflows

Antoine Zambelli's Python framework wraps Ollama, llama-server, and Llamafile agents with rescue parsing, retry nudges, and step enforcement. Show HN hit 293 points; an ACM CAIS '26 demo accompanies the eval suite.

Forge repository social card on GitHub showing the project name and tagline

Drop-in reliability layer that pushes 8B local models toward frontier-API accuracy on tool-calling agents.

Key specs

GitHub stars405
Show hn points293
Show hn comments110
Eval scenarios26
Top self hosted score86.5%
Hardest tier score76%

What is it?

Forge is a small Python framework that sits in front of a self-hosted LLM backend (Ollama, llama.cpp's llama-server, Llamafile, or the Anthropic API) and makes its tool-calling more reliable. The author, Antoine Zambelli, published the project today on Hacker News with the claim that guardrails alone move a Ministral-3 8B model from roughly 53% to ~99% accuracy on a 26-scenario agentic eval. The framework also has a companion demo paper at ACM CAIS '26.

How does it work?

Three guardrail layers wrap each tool call: rescue parsing recovers malformed JSON / tool invocations across model output formats, retry nudges feed errors back so the model can self-correct, and step enforcement gates the workflow on prerequisite conditions. A separate context-management layer enforces VRAM-aware budgets with tiered compaction so long agent loops stay inside hardware limits. Users plug Forge in via a WorkflowRunner, composable middleware, or a proxy server that sits between a client and the local model.

Why does it matter?

Self-hosted 8B models normally cascade-fail on multi-step agents: 90% per-step accuracy still produces a 40% failure rate over five steps. Closing that gap on consumer hardware means privacy-sensitive workflows — code review, incident response, scraping pipelines — can run locally instead of paying frontier API per token. The eval also exposes a 75-point spread between backends on the same weights, which is a load-bearing finding for anyone choosing a server.

Who is it for?

indie devs and researchers running local agents on consumer GPUs

Try it

pip install forge-guardrails

Sources · 3 outlets

Tags

  • agentic
  • tool-calling
  • guardrails
  • local-llm
  • ollama
  • llama-cpp
  • llamafile
  • self-hosted
  • python
  • show-hn
  • open-source

← All releases · Learn AI