Forge
Guardrails take an 8B model from 53% to 99% on agentic tasks
About Forge
A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows - antoinezambelli/forge
Hi HN, I'm Antoine Zambelli, AI Director at Texas Instruments.I built Forge, an open-source reliability layer for self-hosted LLM tool-calling.What it does:- Adds domain-and-tool-agnostic guardrails (retry nudges, step enforcement, error recovery, VRAM-aware context management) to local models running on consumer hardware- Takes an 8B model from ~53% to ~99% on multi-step agentic workflows without changing the model - just the system around it- Ships with an eval harness and interactive dashboard so you can reproduce every numberI wanted to run a handful of always-on agentic systems for my portfolio, didn't want to pay cloud frontier costs, and immediately hit the compounding math problem…
Ratings & reviews
Log in to rate and review Forge.
Discussion (0)
Log in to join the discussion.