Projects
Everything worth listing, newest first, from research systems built at work to things I made because I wanted them to exist.
Selected work06
SuperScout· SuperAGI
Cost-aware routing for coding agents. A 7B model I trained scouts the repository first, and its verified findings decide which frontier model is worth paying for. I built the training pipeline and the evals that benchmarked four frontier models head to head on SWE-bench Pro, where the system matches the best single model at about a fifth the cost per solve.
- 1/5
- the cost per solve
- $86
- to train the searcher end to end
- 3,000+
- agent eval episodes run
SuperCoder· SuperAGI
SuperAGI's open-source, local-first coding agent, which searches a codebase by meaning and call graph rather than grep alone. I built the Rust client for its context engine, and the eval platform behind our paper, running large-scale agentic evals to test whether the index actually helps.
- 10
- languages parsed
- 819
- agent eval runs in the ablation
Digital Employees· SuperAGI
Autonomous AI teammates that join a live meeting with voice and avatar, run the sales demo, answer questions, and drive the slides themselves. I built the backend: the agent loop, the speech pipeline, and the meeting integration.
- 4,000+
- client meetings joined in production
Vibe Coder· SuperAGI
Describe an app, watch it get built, and deploy it to its own subdomain. I owned the execution and deployment side: the sandboxed runtime the agent writes code inside, and the pipeline that ships the result.
- 450+
- apps generated and served
Lifie
Voice and chat AI for businesses, across outbound engagement and inbound support. Co-founded it and own the architecture: the intelligence layer, retrieval grounding, and guardrails.
cc-vault
A terminal UI for browsing and managing Claude Code sessions. Search across every conversation, preview them as rendered markdown, and resume any one of them in place.
Other projects04
Metafog
A decentralised AI search platform running on contributed GPU and bandwidth, with a developer API over the top.
ArXiv RAG
A research assistant over ArXiv papers: semantic search, targeted Q&A, and a fine-tuned Qwen model for domain answers.
BiasBalance
Detects bias in categorical datasets with chi-squared and independence testing, then rebalances them with generated data.
CodeCatalyst
A CLI that sets up a development environment from a description, using agents to resolve toolchains and dependencies.
Earlier03
- Kanban Task ManagerTask dashboard with list and drag-and-drop board views.
- BunkBetterAttendance tracker for students.
- Database Q&A AgentNatural-language querying over a SQL database.