31,700 packages matching “llm-benchmark”
pnpm
v11.21.0 · 2 days ago
Fast, disk space efficient package manager
No known vulnerabilities
pad-left
v2.1.0 · 10 years ago
Left pad a string with zeros or a specified string. Fastest implementation.
No known vulnerabilities
fastest-stable-stringify
v2.0.2 · 8 years ago
Fastest stable deterministic JSON.stringify()
No known vulnerabilities
@types/benchmark
v2.1.5 · 2 years ago
TypeScript definitions for benchmark
No known vulnerabilities
@pipelinescore/mcp
v0.1.1 · 1 month ago
MCP server for the PipelineScore LLM benchmark — exposes run_benchmark / get_user_leaderboard / get_user_profile tools to any MCP-compatible client (Claude Code, Codex, Cursor, Continue, Cline). Lets your AI drive local-first LLM benchmarking on your hard
No known vulnerabilities
looks-same
v10.0.1 · 11 months ago
Pure node.js library for comparing PNG-images, taking into account human color perception.
No known vulnerabilities
css-tree
v3.2.1 · 5 months ago
A tool set for CSS: fast detailed parser (CSS → AST), walker (AST traversal), generator (AST → CSS) and lexer (validation and matching) based on specs and browser implementations
No known vulnerabilities
rate-limiter-flexible
v11.2.0 · 2 months ago
Node.js atomic and non-atomic counters, rate limiting tools, protection from DoS and brute-force attacks at scale
No known vulnerabilities
whynot
v5.0.0 · 4 years ago
Generic VM-based structure matching framework
No known vulnerabilities
superlocalmemory
v4.0.1 · 2 days ago
Local-first agent memory with MCP and an agent-native CLI. Documented clients include Claude Code, Cursor, and Windsurf.
No known vulnerabilities
fast-printf
v1.6.10 · 1 year ago
Fast and spec-compliant printf implementation for Node.js and browser.
No known vulnerabilities
hyperframes
v0.7.107 · 2 hours ago
HyperFrames CLI — create, preview, and render HTML video compositions
No known vulnerabilities
reusify
v1.1.0 · 1 year ago
Reuse objects and functions with style
No known vulnerabilities
@metaharness/darwin
v0.9.1 · 5 hours ago
Freeze the model, evolve the harness. Two measured applications: (1) SWE-bench code-repair — conformant GLM->Opus empty-patch cascade resolves 51.3% Lite (n=300) and 55.6% Verified (278/500, Wilson 95% CI [51.2, 59.9], official swebench gold eval, no gold
No known vulnerabilities
@jonahsnider/benchmark
v6.0.1 · 6 months ago
A Node.js benchmarking library with support for multithreading and TurboFan optimization isolation.
No known vulnerabilities
find-my-way
v9.7.0 · 21 days ago
Crazy fast http radix based router
No known vulnerabilities
@llm-ui/react
v0.13.3 · 2 years ago
Display language model outputs in your React project.
No known vulnerabilities
@stdlib/bench-harness
v0.2.3 · 6 months ago
Benchmark harness.
No known vulnerabilities
@thi.ng/transducers
v9.6.42 · 21 days ago
Collection of ~170 lightweight, composable transducers, reducers, generators, iterators for functional data transformations
No known vulnerabilities
@sentropic/llm-mesh
v0.15.0 · 2 days ago
Provider-agnostic LLM access runtime SDK for Sentropic.
No known vulnerabilities