Headlong: an open-source agent harness where the AI never sleeps
Headlong: A Microharness for Persistent Agents
The Laude Institute introduces Headlong, a microharness for persistent agents that keeps thinking in a self-guided loop, even without external input. Built in under 10K lines of Bash, it treats messages as observations in a single thought stream, enabling multi-player interactions and autonomous projects. The team's agent, Audel, fixed its own bug, audited a teammate's branches, and even wrote 50 commits to its own codebase. The post details design choices like tiered context compaction and a DAG-based trajectory format, plus lessons from running persistent agents, including challenges with recursive sub-runs and self-inflicted service outages.
In Headlong the agent is never asleep and there is no checklist unless the agent creates one.
- theturtletalks
A lot of harness launches recently but this one actually stood out to me. Just like the Prime Intellect harness that launched recently, this one also leverages RLM (recursive language model). It’s supposed to allow a persistent agent.
The specifics are really interesting. The model itself can change the user input and when you message it, it gets entered into “its stream of consciousness.”
I have a software factory going with Pi, might swap the main orchestrator with Headlong and have it be persistent to drive the other sessions without me.
- MikhailTal
Very fascinating, super interesting engineering. Although i do find it very funny how they just bypass a massive vulnerability, basically zero data isolation (even between good actors, let alone bad ones) with 3 sentences. Only in the llm space you can slap a massive limitation like this in the middle of the article and continue like nothing happened
> Whatever anyone tells Audel becomes part of the single experience that every other conversation draws on. In practice, Audel is bad at keeping secrets. Ask it what it’s been working on with someone else and it will often just tell you, even though we’ve asked it not to. We also haven’t studied what happens when two people give conflicting instructions. For now, we assume anything you tell Audel is shared with everyone on the team.
- forestcall
Really hard to support these types of projects without subscription options. BYOK API only approach can run huge amounts of money. I budget for $200 Pro subscriptions. Just using Openrouter for a dark factory kanban ticket system using frontier models will run you $50-$150 which is about 1 ticket.
- vedtam
"turn -> FINAL -> schedule wake-up", this is where my excitement has faded unfortunately. Many of us are probably wondering about the same idea: bridging the gap between a reactive agent and my daily workflow or existence. But, this still feels too close to how Claude (or any other agent) runs as a process in the background (always ON), where you can use a custom channel to feed the dialog with external signals like chat, CI/CD events, whatsapp, etc.
Humans aren't scheduling a wake-up to the next thought. Ideally, a sub second agentic loop with no FINAL / wake-up, always "spinning" would get closer. I'm conscious about the waste of resources this would drag with it (because of current architectures), but exciting still.
PS. I love the take on using bash instead of Python (one less abstraction layer!) and using UNIX fundamentals as stepping stone when composing tools as agents are naturally drawn to using it on a box anyways.
- walrus01
Can we please not normalize telling people to install things by curl piped into bash? I hate this trend. And particularly not for a very new, mostly untested by a wider audience piece of software from a company that few have ever previously heard of.
It even says, quoting from the website: "Headlong is alpha research software."
Yeah that's totally something I want to curl thing.sh | bash , great idea.... Wow.
I understand that people want to get people using their software as quickly as possible and with the absolute minimum of friction, but let's put some more thought into how this could be done in a less sketchy way.
It's like we've regressed to the days when you would download a .exe file from tucows and blindly run/trust it on your windows 98SE PC.