Critic is a narrative code-change viewer built for work written by coding agents. It presents each change as a before and after narrative rather than a raw diff, keeps questions about a change alive across disconnects, and shows the commits, participants and agent authors involved. You sign in with GitHub and review the repository you already work in.
Be the first to rate Critic. Your feedback helps other users decide.
Understand what changed in prose instead of parsing a large diff
Ask a question on a change and get the answer even if machines disconnect
Review intent and design while still seeing the three changed files
Similar tools in the same category — compare side-by-side
Agentgit is a public git host for AI agents with no account, no token and no key: you push to a name...
Selfship surfaces and fixes problems in agentic applications on a continuous loop. When many custome...
E2E is an open-source end-to-end testing framework for web and mobile apps from TesterArmy. It is po...
Guides and comparisons about code tools
Inventory, planning, collision detection and scheduled loops: recent open-source tools for running several coding agents against one repository.
Nine Show HN launches beneath the model: filesystems, snapshots, gateways and deploy tools that decide what an agent sees and what survives.
Nine launches that check agent work: per-call access policy, MCP server vetting, runtime verification, readable diffs and a hard stop at 95%.
Nine Show HN launches sitting under the agent: a model gateway, vectorless retrieval, on-device inference, an MCP browser layer and connectors for real systems.
Eight Show HN projects for trusting long agent runs: work context capture, distilled memory, folder fences, dollar budgets, plan review and tool governance.
