98,211 packages matching “agent-evaluation”

@agentskit/eval

v0.6.2 · 3 days ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

Agent evaluation and benchmarking for AgentsKit.

606Downloads across all versions in the last 7 days, from the official npm downloads API.MITLicense declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v0.6.2 (the latest release), from the OSV.dev database.

@axiom-lattice/agent-eval

v2.1.99 · 11 hours ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

Agent evaluation for Axiom Lattice framework

560Downloads across all versions in the last 7 days, from the official npm downloads API.MITLicense declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v2.1.99 (the latest release), from the OSV.dev database.

autoctx

v0.14.0 · 12 days ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

autocontext — always-on agent evaluation harness

632Downloads across all versions in the last 7 days, from the official npm downloads API.Apache-2.0License declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v0.14.0 (the latest release), from the OSV.dev database.

@wix/evalforge-types

v0.106.0 · 1 month ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

Unified types for EvalForge agent evaluation system

362Downloads across all versions in the last 7 days, from the official npm downloads API.

No known vulnerabilities

Known vulnerabilities affecting v0.106.0 (the latest release), from the OSV.dev database.

@goyamegh/agent-health

v0.5.23 · 1 month ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

Agent Evaluation and Observability Framework

176Downloads across all versions in the last 7 days, from the official npm downloads API.Apache-2.0License declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v0.5.23 (the latest release), from the OSV.dev database.

@opensearch-project/agent-health

v0.5.2 · 26 days ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

Agent Evaluation and Observability Framework

14Downloads across all versions in the last 7 days, from the official npm downloads API.Apache-2.0License declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v0.5.2 (the latest release), from the OSV.dev database.

@verifyax/sdk

v0.3.3 · 5 days ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

Typed TypeScript client for the VerifyAX agent-evaluation REST API.

32Downloads across all versions in the last 7 days, from the official npm downloads API.Apache-2.0License declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v0.3.3 (the latest release), from the OSV.dev database.

@verifyax/mcp-server

v0.3.3 · 5 days ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

MCP server exposing the VerifyAX agent-evaluation platform as conversational tools.

57Downloads across all versions in the last 7 days, from the official npm downloads API.Apache-2.0License declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v0.3.3 (the latest release), from the OSV.dev database.

@forwardimpact/libeval

v0.1.66 · 1 month ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

Agent evaluation framework — prove whether agent changes improved outcomes with reproducible evidence.

64Downloads across all versions in the last 7 days, from the official npm downloads API.Apache-2.0License declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v0.1.66 (the latest release), from the OSV.dev database.

@wundr.io/agent-eval

v1.0.39 · 1 month ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

Agent evaluation framework with LLM-based grading for AI agent quality assessment

37Downloads across all versions in the last 7 days, from the official npm downloads API.

No known vulnerabilities

Known vulnerabilities affecting v1.0.39 (the latest release), from the OSV.dev database.

@fre4x/benchmark

v1.1.7 · 22 hours ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

A deterministic benchmark MCP server for agent evaluation workflows.

3Downloads across all versions in the last 7 days, from the official npm downloads API.MITLicense declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v1.1.7 (the latest release), from the OSV.dev database.

@gnsx/genesys.agent.eval

v1.4.3 · 2 months ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

Agent evaluation harness for benchmarking AI agents against test suites

158Downloads across all versions in the last 7 days, from the official npm downloads API.UNLICENSEDLicense declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v1.4.3 (the latest release), from the OSV.dev database.

agentclash

v2.0.0 · 21 days ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

AI agent evaluation CLI for races, replay, scorecards, and CI regression gates

16Downloads across all versions in the last 7 days, from the official npm downloads API.MITLicense declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v2.0.0 (the latest release), from the OSV.dev database.

harness-evals

v0.2.3 · 1 month ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

Agent-first coding-agent evaluation harness with Docker isolation, skills onboarding, and result reporting.

63Downloads across all versions in the last 7 days, from the official npm downloads API.

No known vulnerabilities

Known vulnerabilities affecting v0.2.3 (the latest release), from the OSV.dev database.

@poofnew/vibe-check

v0.1.1 · 6 months ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

AI agent evaluation framework for Claude and beyond

16Downloads across all versions in the last 7 days, from the official npm downloads API.MITLicense declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v0.1.1 (the latest release), from the OSV.dev database.

@polarityinc/polarity-keystone

v0.3.4 · 2 months ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

TypeScript/JavaScript SDK for the Polarity agent evaluation + sandboxed-execution platform (legacy product name: Keystone)

70Downloads across all versions in the last 7 days, from the official npm downloads API.MITLicense declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v0.3.4 (the latest release), from the OSV.dev database.

redharness

v1.1.0 · 1 month ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

Agent evaluation, regression, & safe red-team security harness with app-specific QA packs

7Downloads across all versions in the last 7 days, from the official npm downloads API.MITLicense declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v1.1.0 (the latest release), from the OSV.dev database.

@tlahey/agent-eval

v0.2.0-alpha · 4 months ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

AI coding agent evaluation framework with Vitest-like DX

2Downloads across all versions in the last 7 days, from the official npm downloads API.ISCLicense declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v0.2.0-alpha (the latest release), from the OSV.dev database.

@artale/pi-eval

v1.3.2 · 3 months ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

Agent evaluation harness. Judge sessions on success, tool usage, efficiency, methodology. Inspired by opencc.

14Downloads across all versions in the last 7 days, from the official npm downloads API.MITLicense declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v1.3.2 (the latest release), from the OSV.dev database.

yggdrasil-mcp

v1.2.7 · 6 days ago

100
0-100 score computed by this site from verifiable signals only: known OSV.dev advisories affecting this exact version, how recently it was published, and the repository's OpenSSF Scorecard.

Reasoning orchestration MCP - Tree of Thoughts with multi-agent evaluation. Fork of Anthropic's sequential-thinking with string coercion fix.

66Downloads across all versions in the last 7 days, from the official npm downloads API.MITLicense declared in the package manifest.

No known vulnerabilities

Known vulnerabilities affecting v1.2.7 (the latest release), from the OSV.dev database.
1 / 50Next