headlong vs prime-agent
Persistent-agency agent harness in ~11K lines of Bash: it keeps thinking between messages, thinks by writing shell commands, and one shared mind serves a whole team over Slack or Telegram. — versus — Self-improving coding/research agent around a Recursive Language Model: persistent IPython as the core tool, programmatic subagents, durable harness state it refines via evidence-backed /refine.
Both are Recursive Language Model harnesses where the agent thinks in code rather than in tool-call JSON. Prime-agent uses a persistent IPython REPL and targets coding/research with evidence-backed self-refinement; Headlong uses Bash and targets open-ended persistent agency.
| headlong | prime-agent | |
|---|---|---|
| Stars | 1.2k | 22k |
| Forks | 128 | 2.4k |
| Language | Shell | TypeScript |
| License | Apache-2.0 | MIT |
| Last activity | today | today |
| Topics | agents, memory | coding, agents |
| Curated connections | 6 | 7 |
headlong — the curator's take
Read this if you think harnesses have converged. Headlong has no tool-calling layer — the model emits shell rather than function calls, so `curl` is the HTTP client and `jq` the JSON parser, with `skills` playbooks and the `mem`/`traj`/ `context` CLIs as the capability layer — and it never stops: your message lands in an ongoing thought stream as one more observation, and the agent decides whether to answer. The trajectory is a fork/merge DAG of jsonl files, and context is a projection of it at exponentially decaying resolution, so nothing is compacted away in place. Laude Institute research alpha: it runs real shell commands around the clock at $1-2/hour, so use a spend-capped key and let the installer put it in Docker. Not the pick if you want a reactive, per-user, request/response coding agent — that mode exists but the whole design is aimed elsewhere.
prime-agent — the curator's take
The two abstractions are genuinely different: context as variables in a persistent REPL (not a transcript), and a harness that rewrites its own supplemental state with rollback — the closest thing to a shipping continual-learning agent. Daemon sessions and agent-to-agent messaging make it a long-horizon tool, not a chat CLI. When NOT: it's a full worldview — you adopt the RLM way or fight it; young codebase moving fast, and self-improvement means your harness drifts from everyone else's.