288 packages matching “judging”
@exercode/problem-utils
v4.2.3 · 1 day ago
:100: A set of utilities for judging programs on Exercode (https://exercode.willbooster.com/).
No known vulnerabilities
@herjarsa/omo-meta-governor
v0.49.0 · 12 days ago
Self-judging agent orchestration layer for OpenCode. Reads memory, scores sessions, dispatches decisions.
No known vulnerabilities
@exercode/problem-utils-llm
v1.0.5 · 1 day ago
Exercode llm judging utilities
No known vulnerabilities
@exercode/problem-utils-browser
v2.1.5 · 1 day ago
Exercode browser judging utilities
No known vulnerabilities
pi-autocontext
v0.10.0 · 1 month ago
autocontext extension for Pi coding agent — iterative strategy generation, LLM judging, and evaluation tools
No known vulnerabilities
@wix/eval-assertions
v0.84.0 · 2 months ago
Assertion framework for AI agent evaluations - supports skill invocation checks, build validation, and LLM-based judging
No known vulnerabilities
deepthonk
v0.3.1 · 7 days ago
Provider-neutral OpenDeepThink CLI and MCP server. Population-based reasoning via pairwise judging and Bradley-Terry ranking.
No known vulnerabilities
judge-dredd
v0.1.1 · 22 days ago
Local kit for ingesting corpora, synthesizing LLM eval questions, reviewing gold, and judging model answers.
No known vulnerabilities
@canner/slate-util-have
v1.5.0 · 8 years ago
Utility functions for judging whether it have something
No known vulnerabilities
exercode
v0.0.1 · 1 month ago
Placeholder for the Exercode CLI (https://exercode.willbooster.com/). For problem authoring and judging, use @exercode/problem-utils (bin: exercode-problem).
No known vulnerabilities
judgejs
v1.0.5 · 8 years ago
A lightweight vanilla JavaScript library for judging
No known vulnerabilities
@j1nn0/agent-retry-guard-pi
v0.2.0 · 22 days ago
Minimal Retry Guard Pi adapter for recording and judging retry attempts, with opt-in automatic failure recording.
No known vulnerabilities
judging-question-toolkit
v1.0.1 · 3 years ago
Toolkit for Judging Question
No known vulnerabilities
print-ypc
v1.0.6 · 6 years ago
A lightweight vanilla JavaScript library for judging
No known vulnerabilities
ev3-judge
v0.1.1 · 10 years ago
Live judging for ev3-client
No known vulnerabilities
@contextpilot/openclaw-contextpilot
v0.1.4 · 5 months ago
IRL-based dialogue and tool interception with PRM judging
No known vulnerabilities
@bryel/evals
v0.2.0 · 28 days ago
Export an eval session's artifacts — screenshots and/or text outputs — to bryel for judging. Framework-agnostic, zero dependencies.
No known vulnerabilities
@j1nn0/agent-evidence-pi
v0.1.0 · 26 days ago
Minimal Pi adapter for recording and explicitly judging caller-declared evidence.
No known vulnerabilities
xstream-drop-repeats-by-keys
v1.1.0 · 6 years ago
An xstream operator to filter out duplicate objects judging by some keys
No known vulnerabilities
eiki
v0.1.1 · 5 years ago
The simplest library for judging values
No known vulnerabilities