Alternatives
Products that do what Forge – Guardrails take an 8B model from 53% to 99% on agentic tasks does
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…
- 1
- 2
- 3
- 4
- 5
- 6WP
Anthropic and OpenAI's publicly available models are explicitly guard-railed so that they refuse offensive tasks. And their cyber-focussed models are gated for enterprises. This leaves SMEs and mid market open to major vulnerabilities. AI can be used as both an adversarial and defensive tool in the world of cyber. A worst case outcome is if only the adversaries have access. Meanwhile, most existing AI cyber tools are just wrappers. The problem is that they still have all the guardrails on from the foundation model where they will inherit its refusals. For this project we've post-trained a…
Jun 2026 · argusred.com
- 7AK
I'm a software engineer who keeps getting pulled into DevOps no matter how hard I try to escape it. I recently moved into a Lead DevOps Engineer role writing tooling to automate a lot of the pain away. On my own time outside of work, I built Artifact Keeper — a self-hosted artifact registry that supports 45+ package formats. Security scanning, SSO, replication, WASM plugins — it's all in the MIT-licensed release. No enterprise tier. No feature gates. No surprise invoices. Your package managers — pip, npm, docker, cargo, helm, go, all of them — talk directly to it using their native…
Feb 2026 · github.com
- 8
- 9OS
We 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…
Mar 2026 · github.com
- 10
- 11AF
I’ve been working on a temporal database for agents that combines graphs, tables, and compute. While building it, I ended up needing an agent framework that could handle both simple tool-use tasks and more graph-based execution, so I pulled that out into a separate project, Agent Forge. Agent Forge uses a two-tier execution model: * a heuristic router decides whether a request is simple or complex * simple requests go through a lightweight agent loop with a single system prompt and tool-calling loop * more complex requests can use memory retrieval, reflection constraints, tree search, and…
Mar 2026 · github.com
- 12
- 13AB
Hey HN! We're building an open-source CMS designed to help creators with every part of the content production pipeline. We're showing our tiny first step: A tool designed to take in a Twitter username and produce an "identity card" based on it. We expect to use an approach similar to [Constitutional AI] with an explicit focus on repeatability, testability, and verification of an "identity card." We think this approach could be used to create finetuning examples for training changes, or serve as inference time insight for LLMs, or most likely a combination of the two. The tooling we're…
2025 · contentfoundry.com
- 14CO
We recently started to use agents to update some documentation across our codebase on a weekly basis, and everything quickly turned into cron jobs, logs, and terminal output. it worked, but was hard to tell what agents were doing, why something failed, or whether a workflow was actually progressing. We thought it would be more interesting to treat agents as long-lived workers with state and responsibilities and explicit handoffs. Something you can actually see and reason about, instead of just tailing logs. So we built Clawe, a small coordination layer on top of OpenClaw that lets agent…
Feb 2026 · github.com
- 15
- 16FC
Hey 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 –…
2025 · tensorblock.co
- 17OA
Hi HN, we're Kiran and Vijay! Over the past two years, we have built a columnar storage engine for observability: logs, metrics, and traces. Today, it's exciting for us to show what we've built on top of that foundation: LLM Agent Observability. Given how non-deterministic agents are, storing all traces without sampling was critical for us. But these traces tend to be in the MBs, sometimes GBs - we needed to store them inexpensively. We also needed the queries and analyses to be fast. To meet both these goals, we store them in S3 in our own parquet-like file format, and query them using AWS…
Jul 2026 · oodle.ai
- 18FS
2025 · github.com
- 19
- 20
- 21CA
TL;DR: we built a framework-agnostic agent runtime that uses gVisor for isolation and runs on k8s. It’s open-source under AGPLv3 Recently we’ve been working on a customer support “AI assistant” - essentially an interactive knowledge base/L1 support but with an option to touch resources that belong to a customer it’s talking to. We found existing tools to be lacking in these aspects: 1. Fully intercepted i/o. We wanted to trace out LLM calls as well as any other networking calls attempted by the harness so that guardrails and audit trails apply to all current and future systems…
Jul 2026 · github.com
- 22
- 23
- 24
Ranked by how close each launch is in meaning, then by votes. Refine with a description →