Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks
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 number I wanted to run a handful of always-on agentic systems…
Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks launched on May 19, 2026 with 687 votes, #8 of 20,538 launches that month and more than 99% of that year's launches.
In plain words
Forge is an open-source reliability layer for self-hosted language models performing multi-step tool-calling tasks. It improves performance on agentic workflows by adding guardrails like retry nudges, step enforcement, and error recovery without modifying the underlying model itself. Designed for smaller models running on consumer hardware, Forge includes an evaluation harness and dashboard to track results. It's built for developers who want to run autonomous systems locally without relying on cloud-based models.
written from the facts on this page · September 2026
From the sources
A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows - antoinezambelli/forge
In the maker’s words, at launch
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…
Does a similar job
all alternatives →
TensorBlock Forge2025 · tensorblock.co · ▲378Hey HN, We just recently launched Forge – an AI model API platform that lets you access and call AI models from multiple providers in one place. Find it on our website: https://tensorblock.co/forge Some key features: Unified API Key – Store multiple provider API keys and access all with a single Forge API key. OpenAI API Compatible – Drop-in replacement for any application that uses OpenAI’s API. Advanced Security – Strong Encryption for API keys with JWT-based authentication. Client Management – Easy key and user management via included command-line interface. Open-source –…
Progress AI ObservabilityAug 2026 · telerik.com · ▲168Hi HN! We’re the team behind Fiddler, and we recently built an Agent Cache feature. It works by capturing an LLM request/response pair and, once caching is enabled, serving subsequent matching calls locally so duplicate requests never hit the provider. It’s meant to reduce three pains that show up together in agent development: token cost, feedback-loop latency, and output non-determinism. We’d love to hear your thoughts.
WhiskerMar 2026 · whisker.spatialkittens.com · ▲94Create and edit CAD models into production-ready prototypes
Open-source playground to red-team AI agents with exploits publishedMar 2026 · github.com · ▲30We build runtime security for AI agents. The playground started as an internal tool that we used to test our own guardrails. But we kept finding the same types of vulnerabilities because we think about attacks a certain way. At some point you need people who don't think like you. So we open-sourced it. Each challenge is a live agent with real tools and a published system prompt. Whenever a challenge is over, the full winning conversation transcript and guardrail logs get documented publicly. Building the general-purpose agent itself was probably the most fun part. Getting it to reliably use…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md
Dev tools · May 2026 · github.com