Forge

AI

agent reliability guardrails

SHOW HN2026

687points
252comments
#26of 4,366 in 2026
Top 1%of 2026 by points

How HN took it

MixedNo clear lean

35 positive, 48 neutral or asking, 1 mixed, 19 critical, out of 103 comments about the project. Thread score +0.12.

Idea: 15 for, 5 againstPerformance: 8 for, 4 againstExecution: 5 for, 2 againstDocs: 0 for, 7 againstDesign: 1 for, 0 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Useful idea of domain-agnostic nudges at the tool call level

    From 1 comment
    • Ah, so it a "smart" retry mechanism?
      k__ on HN

Objections

  • Documentation is unclear about the workflow and guardrail pieces

    From 2 comments
    • The docs should start with that with a very clean explanation how it works. Basically first paragraph. :) Otherwise you should expect churn. But also it should really go into…
      _pdp_ on HN
    • I've just read through your readme and I have zero clue what this does. Something about proxying model calls and applying "policies" to them? But what kind of things does it…
      esperent on HN

Requests

  • Support for LM Studio backend

    From 2 comments
    • Hey this genuinely _fucks_, you're a legend. You can even get stupid good results from the 1 bit bonsai models! Plays v nice with lmstudio It's now completely reasonable to throw…
      monster_truck on HN
    • I couldn't get it working with lmstudio. I have bonsai-8B running with llama-cpp and am attempting to build a harness for it. Looking good so far, I just got it started but Forge…
      tmjdev on HN

Questions

  • How does proxy mode differ from the WorkflowRunner class

    From 1 comment
    • > # External mode — you manage llama-server, forge proxies it > python -m forge.proxy --backend-url http://localhost:8080 --port 8081 This is a good example because I've…
      nzeid on HN
  • Does it work with qwen models and remote APIs

    From 1 comment
    • I'm curious if in proxy mode it works also with remote models or only with local models. Also, did someone tried it with local Qwen 3.6?
      DeathArrow on HN

Alternatives named

  • Simple retry loops around workflows

    From 1 comment

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/48192383)