Part 1: I ragged every conversation I ever had with AI
I ran a privacy preserving analysis on 809 conversations. The results were humbling, surprising, and exactly what I needed to see.
Sybil Solutions / 0xSero
I build production systems at the intersection of AI and crypto. Open-source tools used by developers worldwide. Client work for Ethereum Foundation, ZKSync, GitCoin, and more.
Tools and libraries built in public.
Extract conversations from Claude Code, Cursor, Codex, Windsurf for ML training
Hub-and-spoke multi-agent orchestration with Neo4j memory and 22+ tool APIs
Terminal web browser in Rust with AI chat, multi-engine search, and tool-calling
Graph-based AI memory with scoped isolation and MCP server support
Chrome extension for AI browser automation with orchestrator mode and vision
Fork of OpenAI Codex with multi-agent orchestration and local LLM support
From zero-knowledge research and governance infra to production-ready AI agents, I take on projects at the edge of what's possible and make them boringly reliable.
AI / AGENTS
LLM infrastructure, multi-agent orchestration, tool-calling systems
CRYPTO / GOVERNANCE
ZK protocols, L2 infra, governance event systems, grants tooling
PRODUCT / SYSTEMS
Interfaces that match the depth of the underlying system
What I've been building lately
Multi-agent orchestration with Neo4j memory
80k-160k daily RPC calls → RSS feeds
ZK proofs + IVC for private digital notes
Terminal web browser with AI tool-calling
Contributed To
HeySynpressRaid GuildMetagameScopeLiftAlluoDebtDAOMustang ProtocolPangeaNextMetaEthereum FoundationZKSyncGitCoinSuperfluidMakerDAOGnosisLens ProtocolPOKT NetworkTellorLiquitySagaElizaOS
HeySynpressRaid GuildMetagameScopeLiftAlluoDebtDAOMustang ProtocolPangeaNextMeta"Sybil Solutions brings a powerful blend of talent, integrity, and genuine curiosity. When they take on a task you can relax, knowing that they'll see it through to completion to the highest standards. I recommend them without a heartbeat's hesitation."
I ran a privacy preserving analysis on 809 conversations. The results were humbling, surprising, and exactly what I needed to see.
What happens when you fine-tune a 14B parameter model on your own coding conversations? Real numbers, real costs, and real frustrations.
My journey from spending thousands monthly on AI subscriptions to building a custom 8x 3090 AI rig for local inference
Subscribe for insights on AI agents, blockchain infrastructure, and building in public.