The LLM Evaluation Framework
☆34Feb 8, 2026Updated 9 months ago
Alternatives and similar repositories for ai-eval
Users that are interested in ai-eval are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Agent skills for long-running execution, high-recall code review, and measurable self-improvement loops.☆27Jun 16, 2026Updated 4 months ago
- A Claude Code skill that turns Claude into an infinite development loop: spec → feature list → implement → test → commit → repeat — acros…☆13Mar 11, 2026Updated 8 months ago
- ☆12Jul 18, 2026Updated 3 months ago
- Context-Engineering 实用第一性原理手册 中英双语翻译版,内容详见Chinese-Biligual文件夹，Context-Engineering Chinese Bilingual Translation☆11Jul 14, 2025Updated last year
- The plunge for dsh to boost model's search ability.☆20Aug 18, 2026Updated 2 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- 大 A 资金实时流向☆20May 11, 2026Updated 6 months ago
- An app to monitor the (Codex) situation☆15Feb 3, 2026Updated 9 months ago
- ☆149Sep 21, 2026Updated last month
- ☆14Aug 3, 2025Updated last year
- One Memory. All CLIs. Never Compacted. Exact Search.☆28Sep 5, 2026Updated 2 months ago
- 一款企业级内部golang微服务、单体基础架构技能规范，指导 AI 编写健壮代码。An enterprise-grade internal Go monolithic and microservice architecture skill specification, de…☆13Jun 28, 2026Updated 4 months ago
- Agent skill for turning serious expert interviews into restrained, source-faithful notes.☆19Sep 30, 2026Updated last month
- ContextWeaver 是一个基于 MCP 协议、利用 Tree-sitter 和向量搜索为大语言模型提供本地代码库智能上下文编织与检索的工具。☆296Sep 8, 2026Updated 2 months ago
- Listen. Remember. Evolve. 开源桌面端ai引擎☆62Jun 27, 2026Updated 4 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- go 常用摘要 Hash 算法库 / go hash functions (MD2/MD4/MD5/Hmac/Ripemd160/SHA1/SHA3/SHA256/SM3/kupyna/XXHash/SipHash/Blake3)☆20Jun 21, 2026Updated 4 months ago
- Classification-first framework for designing and reviewing CLIs.☆27Mar 13, 2026Updated 7 months ago
- OpenClaw Agent Skill — 对任意 GitHub 项目进行多源深度分析，输出结构化研判报告☆79Oct 22, 2026Updated 3 weeks ago
- 营销引擎前端-运营系统☆11Oct 21, 2024Updated 2 years ago
- High-performance HTML to Markdown converter with full GitHub Flavored Markdown support. Written in Rust, available for Node.js and as a n…☆12Sep 12, 2026Updated 2 months ago
- Prompt-only RAG with strict citations for in-context documents | 面向上下文内文档的纯 Prompt 引用型 RAG Skill☆33Mar 2, 2026Updated 8 months ago
- ☆27Apr 12, 2026Updated 7 months ago
- CLILoom brings agent harnesses, visual workflows, and real terminals together in one desktop workspace. Quickly design, customize, and pl…☆12Nov 4, 2026Updated last week
- ☆17Sep 17, 2026Updated last month
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- jspm.org website☆14Nov 3, 2026Updated last week
- Lightweight standalone backend for GEO platform — user accounts, billing, API proxy, ticket system, and sqladmin panel.☆16Apr 14, 2026Updated 6 months ago
- 一个会盯着简历漏洞追问的 AI 模拟面试官，支持微信和命令行。☆16May 12, 2026Updated 6 months ago
- ☆14May 29, 2026Updated 5 months ago
- industrial-agent☆19Jul 25, 2026Updated 3 months ago
- Pi fork with the executable companion course for 《动手学 Pi》 on course/build-your-own-pi☆21Jul 21, 2026Updated 3 months ago
- HookCodeGenerator Plugin for IntelliJ IDEA. 适用于idea的hook代码生成器☆14Nov 28, 2023Updated 2 years ago
- warp2api_register☆10Oct 19, 2025Updated last year
- The open source coding agent. openai anthropic gemini☆467Apr 2, 2026Updated 7 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆16Jun 2, 2026Updated 5 months ago
- ☆49Aug 9, 2025Updated last year
- 聊天就是CRM - claude skill 做一个crm，直接通讯聊天管理crm - 在claude code , openclaw 方便使用 claude code , openclaw 是有记忆功能，但是crm往往比较复杂和严肃，如果有一个系统的crm整理客户信息，…☆13Feb 3, 2026Updated 9 months ago
- ☆11Feb 5, 2017Updated 9 years ago
- Catches and repairs AI hallucinations before delivery: three quality gates, 31 built-in rules, a self-healing loop and a 90-point accepta…☆316Sep 8, 2026Updated 2 months ago
- 提示词优化工作台：多轮自动优化与评分，支持人工接管和完整提示词交付☆215Updated this week
- 这是一个集百家的二进制MCP，高效、简单、开源是核心。三术MCP☆264Updated this week
Are these results useful?