Tips for improvement, resources, DSA, math, verdicts, time complexity, ratings, contest, interesting things
Token-efficient browser verification for AI coding agents
Verified agents — nothing is "done" until a grader returns a verdict. Eyes (AgentVision) + verdict bus + compounding memory + a fleet + agent-built tooling + agent-run CI/CD.
🧑⚖️ Evaluate AI skill and agent performance with configurable scores and dual-mode operation on Claude Code and Cowork platforms.
OpenClaw skill: 比价 + verdict + 购买链接 一体化（含本地历史价积累 + 飞书多维表格同步 opt-in）— price comparison, buy links, local price history for OpenClaw
Governed verification and synthesis for Massive Intelligence (IM) outputs: configurable Thinker, Worker, and Verifier panels, model-as-judge, and Ed25519-signed, SHA-256-chained tamper-evident verdicts. Zero dependencies, node-free core, TypeScript-first.
Node-RED nodes for talking to Wildfire
Verdict is a Reversible Decision Primitive for Many Workers Acting on Tentative Facts While Controllers Later Promote, Contradict, Expire, or Compensate Decisions Without Re-running the Original Work.
Evaluation discipline for agentic apps — a vendored, local-first LLM-evaluation framework operated through your coding agent, with typed authority and a single Verdict Engine that gates only what you approve. The pure core; you decide what to measure and it derives no metrics on its own.
Deterministic certification platform — kernel + N domain packs (4th of the -stra family; the first platform emitted by the HELIX Condense recipe from the robotics/release cluster)
Plugin insight center — one answer to 哪些值得装: plugin_guide (needs), recipe (environments), plugin_rank (health scores), plugin_audit (security scan), plugin_verdict (install decision)
Add a description, image, and links to the verdict topic page so that developers can more easily learn about it.
To associate your repository with the verdict topic, visit your repo's landing page and select "manage topics."