Hacker News new | ask | show | jobs
Show HN: Weak Incentives – lean, minimalistic toolkit for background agents (github.com)
3 points by andreisavu 222 days ago
A minimal, typed scaffold for agents: deterministic prompts, strict JSON, and a session that records plans, tool calls, and staged edits—so you can replay runs and ship audit logs.

* Deterministic Markdown prompt trees (dataclass input/output, tool contracts)

* On‑disk overrides with hash checks; Git‑root discovery

* Event bus (ToolInvoked/PromptExecuted), reducers, rollbackable session state

* Built‑ins: planning, sandboxed VFS, Python‑eval (via asteval)

* Optional adapters: OpenAI/LiteLLM conversation loop + JSON‑Schema outputs
1 comments
andreisavu 222 days ago
If you try it, I’m most interested in where the abstractions are too thin or too heavy or lacking.

Install: uv add weakincentives (extras as needed)

Start with the code‑review example; it ties together prompt construction, overrides, telemetry and using the adapters.

Status: Alpha; APIs may change

Roadmap: parallel sub-agents, built-in GEPA prompt optimizer that uses the overrides store

link