Queued to studysemantica-agi/semantica
Graph-native context, provenance, ontology, and accountable-AI layer for agents — the #1 repo out of the Sept 9 run.
hub Inspectable Agent Systems
code Open Source
What I'm studying, building with, and contributing to.
Not a GitHub mirror — the repositories currently informing the lab's active projects, and why each one matters.
Queued to study
Queued to studyvolcengine/OpenViking
A live context database unifying memory, RAG, and skills — a concrete agent-memory architecture to test against Semantica.
hub Inspectable Agent Systems
Queued to studybrowser-use/browser-use-pi
Four days old and already worth dissecting: a minimal, evaluation-driven browser agent — small enough to fully understand.
hub Inspectable Agent Systems
Queued to studyNousResearch/hermes-agent
A mature reference for orchestration, delegation, MCP auth, and desktop/browser control — a benchmark baseline, not something to adopt wholesale.
Queued to studyTauricResearch/TradingAgents
Role-specialized multi-agent debate over financial data — direct overlap with agent-systems research, and linked to an arXiv paper.
Queued to studypydantic/pydantic-ai-harness
A compact, typed harness — a clean baseline for comparing ergonomics, correctness, and observability against heavier frameworks.