Open source
Projects
Things I've built in agentic AI and LLM engineering — from reinforcement learning for reasoning agents to the production runtime, caching, and evaluation tooling that agents need to ship.
AgentFlow-Pro
· Agentic RL ResearchProcess-supervised RL that taught an 8B model to reason better — and the gain transferred to a domain it never trained on.
GuardLoop
· Production Agent RuntimeA guardrail runtime for async agents: pre-flight cost/token/time budgets, per-tool circuit breakers, and OpenTelemetry spans — no agent rewrite.
SmartMemo
· Semantic LLM CacheA semantic cache for LLM agents where a learned classifier — not raw cosine similarity — decides when a cached answer is safe to reuse.
Orchflow
· Agent Orchestration FrameworkA dependency-free Python framework for readable multi-agent pipelines: sequential, parallel, conditional, and resumable flows.
agenteval
· LLM Evaluation ToolingBehavioral eval for agents: replaces brittle exact-match asserts with repeated-run pass-rate scoring for CI gates.