108,925 packages matching “eval-agent”
@jetty/eve
v0.3.1 · 9 days ago
Jetty × eve — an eve extension that live-grades an agent's turns with Jetty, steers a reply-style bandit from the grades, and reports eve evals into Jetty
No known vulnerabilities
expr-eval
v2.0.2 · 6 years ago
Mathematical expression evaluator
2 high
nia-web-eval-agent-mcp
v1.0.8 · 1 year ago
NIA AI Web Evaluation Agent MCP Server - Autonomous browser testing and debugging
No known vulnerabilities
ts-node
v10.9.2 · 2 years ago
TypeScript execution environment and REPL for node.js, with source map support
No known vulnerabilities
content-security-policy-parser
v0.6.0 · 2 years ago
Parse Content Security Policy directives.
No known vulnerabilities
cycle
v1.0.3 · 12 years ago
decycle your json
No known vulnerabilities
@tangle-network/agent-runtime
v0.142.3 · 1 day ago
Shared task-lifecycle skeleton for agents: a recursive loop kernel for chat turns, one-shot tasks, and multi-attempt loops, with trace capture and eval-gated self-improvement. Domain behavior lives in adapters; scoring and ship-gates in @tangle-network/ag
No known vulnerabilities
@pixi/unsafe-eval
v7.4.3 · 1 year ago
Adds support for environments that disallow support of new Function
No known vulnerabilities
agent-base
v9.0.0 · 4 months ago
Turn a function into an `http.Agent` instance
No known vulnerabilities
@agent-inspect/eval
v6.17.2 · 5 days ago
Deterministic local eval utilities for AgentInspect traces
No known vulnerabilities
@vercel/agent-eval-playground
v0.1.3 · 6 months ago
Web-based playground for browsing agent-eval experiment results
No known vulnerabilities
@rulvar/evals
v1.246.0 · 22 hours ago
Rulvar evals: eval cases, golden outputs, rubric and judge graders, matrix sweeps, canary fingerprint.
No known vulnerabilities
proxy-agent
v8.0.2 · 2 months ago
Maps proxy protocols to `http.Agent` implementations
No known vulnerabilities
@metaharness/weight-eft
v0.1.1 · 1 month ago
Fine-tune cheap open-source LLMs (GLM, Qwen, DeepSeek) on your AI coding agent's successful runs with LoRA (SFT + DPO) so your model cascade escalates to expensive frontier models (GPT, Claude) less often — cutting cost-per-resolved. Turns run history int
No known vulnerabilities
https-proxy-agent
v9.1.0 · 2 months ago
An HTTP(s) proxy `http.Agent` implementation for HTTPS
No known vulnerabilities
safe-eval
v0.4.1 · 8 years ago
Safer version of eval()
4 critical · 1 high
@aws-sdk/util-user-agent-node
v3.973.59 · 6 days ago
[](https://www.npmjs.com/package/@aws-sdk/util-user-agent-node) [](https://www.npmjs.com/
No known vulnerabilities
tamedevil
v0.1.1 · 3 months ago
Build and evaluate JavaScript strings safely via tagged template literals
No known vulnerabilities
@agentskit/eval
v0.6.3 · 7 days ago
Agent evaluation and benchmarking for AgentsKit.
No known vulnerabilities
@aws-sdk/middleware-user-agent
v3.972.73 · 6 days ago
[](https://www.npmjs.com/package/@aws-sdk/middleware-user-agent) [](https://www.npmjs.c
No known vulnerabilities