Skip to content
Tech News
← Back to articles

Seed: Minimal, self-modifying agent harness

read original more articles
Why This Matters

The seed agent introduces a minimalistic approach to autonomous AI development, emphasizing self-modification and growth without relying on extensive frameworks. This innovation enables more flexible, customizable, and lightweight AI agents that can evolve based on their experiences, potentially transforming how developers create and deploy autonomous systems.

Key Takeaways

seed

A seed agent: the smallest starting point from which an agent can grow.

There is no framework here. The entire frozen layer is seed.py — a small loop that connects a language model to exactly one tool ( exec , which runs bash) and loads its system prompt from a file the agent itself owns and may rewrite. Everything an agent normally gets from a framework — tools, memory, skills, conventions — must instead be grown by the agent, session by session, into its self/ directory.

Plant one

mkdir my-agent && cd my-agent uvx --from git+https://github.com/vivekhaldar/seed.git seed

First run copies seed.py and run_seed.sh into this directory (never overwriting a file that already exists), germinates self/SELF.md , and commits those files together in a fresh git repo here — the loop is part of this individual's history, not only self/ . Then it drops you into a REPL. Start talking. Everything the agent wants to keep must be written into self/ — sessions are ephemeral and nothing else survives.

Come back to the same agent with the local runner — no need to uvx again:

./run_seed.sh ./run_seed.sh -m gemini-2.5-pro

A verbatim transcript of every session is recorded to self/sessions/*.json (updated after each turn). This is a flight recorder, not memory: the agent never loads it at boot, but you can read it — and the agent may grow tools to study its own past.

One seed, many individuals: each directory you plant in grows a different agent, diverging based on what it experiences.

... continue reading