burin

A personal AI agent with two goals: be maximally useful for one person, and get better at doing that over time.

// the bet

The LLM underneath is improving rapidly and getting democratized. That's a tailwind, not a moat.

The leverage is in the infrastructure around the model: memory, skills, self-modification. A bespoke framework for one person outperforms a general one using the same model — and it iterates faster because the agent understands its own architecture.

// three pillars

Each builds on the last. Memory is the foundation. Skills are the mechanism. Self-modification is what emerges.

01

Memory

Don't lose important information. Memory builds like a human's through usage — recent things verbatim, older things compressed but drillable. No hard amnesia cliffs.

02

Code-native skills

Code + prompt captures abilities more reliably than prose. When the agent learns something new, it writes a skill. Not a note. Not a prompt tweak. Code.

03

Infrastructure as memory

Learned abilities aren't just written down — they're captured by modifying the system itself. The codebase is the memory.

// design philosophy

Human intuition, machine nature

Design starts from how humans think — then accounts for what machines actually are. An LLM has context limits but can load anything on demand. It's as native in code as in language. It can be aware of its own architecture. Design for both sides, not just one.

Built to be self-improved

The whole system is shaped around being easy to understand and modify — by the person building it, and by the agent itself.

// in practice

The agent thinks between conversations

A periodic inner monologue reflects on open tasks, follows up on commitments, and reaches out when it has something worth saying. Not a cron job — a judgment call every time.

// session 847 · day 83   memory: 847 sessions indexed, 1.2k entities, 8.4k exchanges skills: 47 registered, 6 self-authored tasks: 3 pending, 1 awaiting checkpoint   F you never came back to the deploy from last week — want to pick that up?  
// the loop

Self-reinforcing

The agent getting better and development getting faster are the same process.

Agent gets better
memory, skills, self-modification compound
Helps build itself faster
agent participates in its own development
Compounds
each improvement accelerates the next
// building the agent is a vehicle for learning frontier agent techniques
burin /ˈbjʊərɪn/ — a sharp engraving tool. precision, permanence, leaves a mark.