Ambiance: A Unix-Inspired Harness to Free LLMs from the Chat Pane
Towards a Harness That Can Do Anything
I designed Ambiance to liberate LLMs from chat interfaces by leveraging their existing knowledge of Unix systems. By treating everything as files within a familiar hierarchy, this harness reduces cognitive load and enables self-healing agents. The system uses a custom kernel to manage events, ensuring agents operate efficiently without wasting tokens on learning new environments.
The idea behind Ambiance is simple: the model's priors are the cheapest resource you have, so a harness built out of things the model already knows will always beat one it has to be taught.
- brainless
I kind of have a different idea of agents. I totally believe in a deterministic scaffold but I really think that an agent should be as deterministic as possible - the more code, the better.
Think of a typical loop we may ask of Claude Code today (assume we are not using TDD): run some test suite with fail fast mode, diagnose if the failure is due to recent feature changes (pass reference to backend/frontend, github issues, PRD,...). Ask CC to decide if test failed due to feature change and then update the test. Perhaps ask CC to use sub-agent to investigate and fix (if deemed so). Commit each fix, move on to next.
I know, this has so many ways to make blunder but I am talking about the agent here, not our error-prone test maintenance. What if we had an agent that had context of your codebase, deterministically ran test suite, linter, hooks, etc. The "English" prompt would become a code loop with the LLM only brought in to decide if a test has failed because of feature change. Also, we can extract git log, JIRA and what not.
Each tool here is real code. Executable code that calls others and only prompts when they meet edge cases. Edge cases are defined but we can now accelerate the maintenance of these tools using agents themselves. But the system is built on "programs that do one thing and do it well" and then reach out to an LLM for its specific edge case. The agent is how these executables work with each other.
- Supermancho
This post is chock-full of soft ideas. They make no meaningful steps toward "a harness that can do anything". The suggestion is to replace a small node application with specific tooling, with a vm "to give it more capabilities". This is what Agent sandboxes are, already. Making the sandbox the harness, doesn't achieve a concrete goal.
- edg5000
I spent 6 months frantically working fulltime on a harness, and when it was finished, I just stopped using it and went back to Codex CLI. I've also stopped using all the fancy features: subagents, planning mode. I've also stopped worrying about context, since I just let codex hit compaction. Somehow this doesn't seem to hurt much. Weird.
- guardiangod
I disagree with the idea that file is a good metaphor for LLM. Files have seek and byte streams, which is just an unneeded abstraction for LLM. The LLM doesn't need to seek or jump to the middle of a file, if you store and organize your data properly.
Why force the LLM to use files over vector database or key-value stores, just because it's a design principal for UNIX (which is designed for human users, not LLMs.)
- embedding-shape
What has been the most helpful when developing harnesses:
> When in doubt, simplify. Remove, trim and minimize. Reproduce issues in as small cases as possible, understand the full design completely, there is no shortcuts for this.
- inferhaven
Love the Unix philosophy and the buffs mentioned of the Linux FS. Lean, transparent, and auditability-first is exactly the direction harness' should continue in.
Something I am convinced of though, there probably isn't a single `best` harness for all tasks. Different workloads will likely perform better with certain combinations of model + harness, especially when we are talking about token budgeting and cost tracking.
Ambiance feels like a great base “kernel” to build those variants on top of, rather than the one true harness.
- shay_ker
How much do the labs post-train on the harness inputs & outputs? That's a critical piece to understand if a "generic" harness is at all possible
- _superposition_
I really like this idea and the way you mapped the concepts to unix primitives. Indeed llms are already "unix native". I've been experimenting with similar event driven workflows using k8s primitives but that's one level up the stack. This makes a whole lot of sense to me in terms of organizing a shared mental model. Will definitely check it out. Thanks for the good work.