hermes-agent VS forgecode

NousResearch publishes a detailed security policy for Hermes Agent. It is unusually clear about what the project treats as load-bearing and what it does not. If you operate Hermes in the cloud, read it first; this post is the operator-friendly companion, not a replacement.

OpenCode seemed perfectly workable as a programming assistant. As personal assistants, they all fall short. It's too difficult to really shape their output.

I was briefly impressed with OpenClaw a few times, but ultimately was turned off by not being able to get the models to stop being so damnably verbose. I thought I made progress for a while by having it tweak its soul, iterate, switch models, iterate, switch models, fuse the results, iterate... but ultimately it's all forgotten early in each session. And then one day it killed itself by rebuilding the container it was inside.

Hermes apparently has some plagiarism issues they're trying to cover up [0] and I was deeply unimpressed with their janky, flickery CLI that force-enables a bulky obnoxious header.

Nanoclaw and nanobot seemed fine, but not notably different. There were some common bugs and glitches that caused some minor data loss while configuring nanobot. After that I just deciding to start hacking my own together.

What I really want in a harness is being able to actually control and rewrite the entire context window, like Zed's Text Threads before they obnoxiously and inexplicably removed what, to me, was their most powerful and distinguishing feature.

[0] https://github.com/NousResearch/hermes-agent/issues/10232

I've opened a design discussion to argue this out before anyone writes a line of it, because a surprise PR to a security-sensitive module is the wrong way to start. Feedback from people who've thought about supply-chain trust is what I appreciate.

Source: https://github.com/NousResearch/hermes-agent

Hermes Agent is an open-source AI agent framework.

I opened my Hermes Agent logs and found something I did not know existed: an auxiliary: block with twelve background tasks. Compression, web extraction, vision, session search, skills matching — all running silently every time I typed a message. Every task was set to provider: auto. And because I had no API keys for the fallback chain, every one silently fell back to kimi-k2.6, my one-trillion-parameter main model.

The adjacent tools worth tracking: the OpenAI Chrome plugin, BrowserCode, Autobrowse, browser-harness, Pi browser extensions, and Hermes browser skills. [13] [14] [6] [15] [16] [12] The category is logged-in browser work: support queues, internal tools, research, scraping, QA, admin ops, and anything where the useful data sits behind a session.

hermes-telemetry solves both by giving you real-time observability and automatic budget enforcement for Hermes Agent.

If you haven't encountered it yet: Hermes Agent is an open-source agentic system from Nous Research. The key differentiators that caught my attention:

I'm using forge code (https://forgecode.dev/) with various local and cloud models and I really like it. MiniMax 2.7 is really great with it, and the new Qwen 3.6 35B A3B feels much stronger, after some testing, than the 3.5 version.

ForgeCode is not an AI model. It's a model-agnostic agent harness, open source under Apache 2.0, written in Rust, that wraps any LLM through OpenRouter or direct API keys. It launched in late January 2025 and hit v2.8.0 on GitHub by April 2026 with over 6,000 stars.

Or maybe this is the push to try something else entirely. ForgeCode currently tops TermBench 2.0 and has been getting a lot of attention. I haven't switched yet, but I'd be lying if I said I wasn't curious.

I tested these models using Forgecode. Want to run them in your own terminal? Install Forgecode⛵

Documentation - Setup guides and API reference GitHub Repository - Source code and issues Discord Community - Support and discussions Release Notes - Complete changelog

What's interesting is that our architectural constraints don't just make code review faster, they actively teach our Agent to generate better code. Every time agent sees our patterns, it learns and add them in memory. In Forge we call it custom rules. Other agents call them memory, rules etc.

👨‍🚀 From Moon Missions to Your Codebase Let your own coding assistant land your next software mission. 👉 Access your Forge dashboard

Shell-based agents respect the developer’s autonomy and expertise. They expose each step they take (just as normal shell commands do) and invite you to refine or approve actions. Using a shell agent feels like collaborating with a teammate in the terminal, rather than outsourcing tasks to a black box. In a shell environment, you can inspect and modify every command the agent runs. For example, if the AI suggests a code change via a script or regex, you see exactly what it does (and can tweak or undo it). This transparency means nothing happens without your knowledge. The developer remains in control: you issue the query, then fine-tune or approve the AI’s suggestions, rather than being bound to a hidden process.