software-engineering-agents

Bug Hunt Bench: 105 real bugs in two production repos, frontier coding models (GPT-6, Claude, Grok, Gemini, DeepSeek...) find and fix them in their own CLI, graded blind. Live leaderboard + every receipt.

An autonomous AI developer that spins up a secure cloud sandbox, writes code, runs tests, and relentlessly self-corrects until the GitHub issue is solved. Built with LangGraph.

A disciplined 10-stage autonomous agent pipeline (Reflexion, Tree Search, ReAct) for Claude Code and AI coding agents. Lifts local LLMs to senior engineering quality.

Codex-native OZM skill pack for AI coding agent governance, agentic coding loops, claim ceilings, and AGENTS.md-aware workflows.

Advanced Closed-Loop Agentic Engineering: Self-healing code loops, automated test-driven synthesis, reflective execution feedback, and autonomous multi-agent software engineering pipelines.

Autonomous code review & remediation engine with LibCST patching, event-sourced FSM orchestration, sandboxed verification, and authenticated human approval.

A conversational AI concierge built end-to-end by a six-agent orchestrated development workflow — specialised AI personas that spec, build, review, and merge their own PRs behind deterministic hooks and a merge gate.