Unclaimed profileBuilt from public GitHub and Hugging Face activity. Brad has not joined Lounge yet.Claim it
Not on Lounge yet
Brad Kinnard
developerAI Systems Architect & Research Engineer. Building AI agents, memory systems, local AI, and developer tools. 20+ years in software and web d
Public projects
swarm-orchestrator
Swarm Orchestrator: a coding agent that must prove its work. Bounded repository changes, the project's real checks as sealed gates, challenges to weak evidence, retries that cannot trade away test quality, and a signed, hash-chained evidence record anyone can verify offline.
JavaScriptagent-orchestrationagentic-aiai-agents
tracemantle
Validate SKILL.md files, track agent-skill bundle changes, and check release evidence against trusted policies.
Pythonagent-skillsagentskillsai-agents
ruleprobe
Translate instruction files into ESLint configs, detect drift, and extract rules
TypeScriptagents-mdaiast
quantproof
Run your real task on quantized models and get measured quality, latency, and peak VRAM, plus the smallest quant that holds quality.
TypeScriptclievaluationllm
rlfusion-orchestrator
Local-first RAG chatbot. An offline RL policy picks per-query weights between an answer cache and a knowledge graph; a critique LLM scores every turn.
Pythoncqlfastapigraphrag
swarm-verify
Swarm Verify: independent verification for software changes from AI coding agents or humans. Runs a project's real checks, separates what passed from what was established, names what stayed unmeasured, and records evidence anyone can check. CLI, GitHub Action, Claude Code hook, MCP server, pre-commit hook.
ai-coding-agentsclicode-quality
Likely stack
ClaudeLangGraphLlamaOllamaCursorMCPFastAPI