Category: Building Jarvis

Open research notes on building Jarvis — a persistent, self-improving AI agent. One paper at a time.

SEAHORSE: What Actually Makes an Agent Code Well

File leases, a bible that asserts shape not liveness, four premises, and the harness. v1.0.
MAESTRO: What Orchestration Actually Buys — A Taxonomy of Latency, Capability and Supply

Orchestration is a scheduler, not an intelligence multiplier. Latency vs capability vs supply — three axes, three cost structures.
STRIATUM: Learned Personality Modulation — Tuning an Agent’s Behaviour from Feedback, Not Static Prompt Text

Your agent’s personality is hand-written prose in a prompt file — and the one mechanism meant to tune it from feedback has injected exactly zero bytes…
BROCA: Giving Agent Recipes a Grammar — A Gradual Type System and Combinator Algebra for Self-Composing Workflows

BROCA gives agent recipes a grammar: a gradual typed value model, compile-time contracts, a sandboxed control grammar, a combinator algebra, a skill standard library, catchable recovery,…
SALIENCE: The Death of Fixed Thresholds, the Pyramid of Significance, and Cheap Traversal as the Basis of Next-Generation Vibe Programming

Relevance must be re-computed from the live situation — not read off a frozen list. SALIENCE argues for three pillars: kill fixed thresholds, order knowledge as…
Instant Recall: A Pre-Computed Concept Index for O(1) Memory Retrieval in Persistent AI Agents

Your agent has the answer in its memory and still can’t find it; Instant Recall builds an offline concept index so retrieval is a constant-time lookup…
Fractal Reasoning: Multi-Resolution Memory and Self-Similar Metacognition for LLM Agents

Your agent’s memory is flat — one zoom level — so it fetches a fact or a gist, never both; Fractal Reasoning indexes memory and structures…
Identity Persistence: Keeping an LLM Agent’s Personality Stable Across Sessions, Model Swaps, and Restarts

Your agent keeps every fact and still stops sounding like itself — Identity Persistence pins the persona every turn, compacts the task without flattening the voice,…
Sleep Consolidation: How Nightly Prompting Makes a Stateless Agent Get Better Over Time

A stateless AI agent that gets 79% fewer incidents over 30 days — not by fine-tuning, but by a nightly loop that rewrites its own operating…
Round Table: Exploiting Cognitive Diversity as a Computational Resource in Persistent AI Agents

Stop asking which model is best and picking one — Round Table puts Claude, GPT, and Gemini at the same table, casts each to the role…