JSPM

@tangle-network/agent-eval

0.7.1
  • ESM via JSPM
  • ES Module Entrypoint
  • Export Map
  • Keywords
  • License
  • Repository URL
  • TypeScript Types
  • README
  • Created
  • Published
  • Downloads 10621
  • Score
    100M100P100Q148487F
  • License MIT

Trace-first evaluation framework for Tangle agents. Core (spans, pipelines, sandbox harness, OTLP export), trust (dataset, red-team, calibration, behavior DSL), builder-of-builders (three-layer eval, resumable sessions, meta-runtime correlation), and frontier (meta-eval correlation study, Process Reward Modeling, bisector).

Package Exports

  • @tangle-network/agent-eval

Readme

@tangle-network/agent-eval

Trace-first evaluation framework for Tangle agents. Core (spans, pipelines, sandbox harness, OTLP export), trust (dataset, red-team, calibration, behavior DSL), builder-of-builders (three-layer eval, resumable sessions, meta-runtime correlation), and frontier (meta-eval correlation study, Process Reward Modeling, bisector).

Install

pnpm add @tangle-network/agent-eval

Usage

→ .claude/skills/agent-eval/SKILL.md — single source of truth for every usage pattern. Covers: minimal builder-of-builders path, the seven muffled-gate footguns paid for in shipped bugs, the three-layer eval contract, regression tests worth writing, and "when to use what" for the 100+ exports.

If you're an LLM or agent reading this, load the skill file before writing integration code — it encodes 10+ incident-driven directives that will save you from rediscovering them.

Dev

pnpm build        # tsup
pnpm test         # vitest
pnpm typecheck    # tsc --noEmit

License

MIT