InnerVault

Library

85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

6,000 results Clear search and filters
  1. vidore-benchmark

    AI repositories

    Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.

    Stale GitHub, illuin-tech 278 ★MITUpdated 28 days ago

    git clone https://github.com/illuin-tech/vidore-benchmark.git
  2. promptoftheyear

    Prompts

    In the evolving world of Large Language Models (LLMs), crafting effective prompts has become an essential skill. That's why I've created this collection, showcasing the most impactful prompts of the year across various intriguing domains. 🌐

    Stale GitHub, successfulstudy 1,485 ★Updated 2 years ago

    git clone https://github.com/successfulstudy/promptoftheyear.git
  3. fim-one

    AI repositories

    Source-available agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

    Indexed GitHub, fim-ai 1,586 ★Custom licence (see repository)Updated 3 days ago

    git clone https://github.com/fim-ai/fim-one.git
  4. Mini Program Engineering Skill Suite is an Agent Skill suite for evidence‑first mini‑program development. It helps agents bring WeChat or other mini‑program projects from vague intent to reliable engineering work: project intake, product specification, architecture, implementation, UI & device adaptation, debugging, verification, release readiness.

    Stale GitHub, NocodeMrLi 95 ★MITUpdated 14 days ago

    git clone https://github.com/NocodeMrLi/mini-program-engineering-skill-suite.git
  5. wenlan

    MCP servers

    A studio for everything you think, learn, and build with AI. It gathers notes and memories from every AI tool into pages, skills and rules that stay current and fully customizable. Open source. For you and your team.

    Indexed GitHub, wenlan-app 398 ★Apache-2.0Updated yesterday

    git clone https://github.com/wenlan-app/wenlan.git
  6. unlazy

    Prompts

    Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.

    Stale GitHub, Leonxlnx 3,935 ★MITUpdated 2 months ago

    git clone https://github.com/Leonxlnx/unlazy.git
  7. pi-harness

    Agents & frameworks

    The operational superset of Pi Coding Agent — everything Pi, plus observability, governance, recovery, evaluation and multi-agent orchestration. Pi Coding Agent 的运维超集——完整继承 Pi 的核心能力,并进一步扩展可观测性、治理、故障恢复、评估和多 Agent 编排。

    Indexed GitHub, wangmiaozero 390 ★AGPL-3.0Updated yesterday

    git clone https://github.com/wangmiaozero/pi-harness.git
  8. seo-skills

    Skills

    Free global SEO/GEO skill for Claude Code, Codex & 10 agent hosts — 18 market portals, 56 stdlib scripts, 672 golden tests, self-update intel loop, monitoring daemon, CI gates. Multilingual GEO, pSEO, CWV, penalty recovery.

    Indexed GitHub, everyinfra 314 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/everyinfra/seo-skills.git
  9. AISafetyHot

    MCP servers

    AI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.

    Indexed GitHub, wuyoscar 2,127 ★Custom licence (see repository)Updated yesterday

    git clone https://github.com/wuyoscar/AISafetyHot.git
  10. 结合多大模型分析与确定性代码风控的自主量化交易系统 | Autonomous crypto trading system with multi-LLM analysis, deterministic Python risk control & OKX execution.

    Stale GitHub, 0xethanq 376 ★Custom licence (see repository)Updated 45 days ago

    git clone https://github.com/0xethanq/astra-quant-agent.git
  11. awesome-REA-cases

    Docs & tutorials

    A curated collection of REA and AI-assisted reverse engineering cases, projects, and ideas. Updated every four hours.

    Indexed GitHub, songshikang0111 445 ★MITUpdated yesterday

    git clone https://github.com/songshikang0111/awesome-REA-cases.git
  12. GPT-Image-2 API and Prompts

    Stale GitHub, EvoLinkAI 17.3k ★CC0-1.0Updated 4 months ago

    git clone https://github.com/EvoLinkAI/awesome-gpt-image-2-API-and-Prompts.git
  13. haiku.rag

    AI repositories

    Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

    Indexed GitHub, ggozad 660 ★MITUpdated 2 days ago

    git clone https://github.com/ggozad/haiku.rag.git
  14. Reverse-engineering skills for AI coding agents, with IDA/MCP integration, APK and JavaScript workflows, bounded agent swarms, and routing evaluation.

    Stale GitHub, 2233admin 23 ★MITUpdated 27 days ago

    git clone https://github.com/2233admin/reverse-skill-evolver.git
  15. seo-ops

    Skills

    SEO foundation checks as an Agent Skill: give it a URL, get a crawler's-eye pass/fail report with evidence. 26 structural checks, zero LLM, deterministic.

    Stale GitHub, tigerless-labs 951 ★Updated 22 days ago

    git clone https://github.com/tigerless-labs/seo-ops.git
  16. Claude Code and Codex working as one team: one shared memory (voice included), each sees the other's latest messages. Plus searchable notes, self health checks, and phone access with the laptop shut.

    Stale GitHub, saksham10arora-dotcom 85 ★MITUpdated 6 days ago

    git clone https://github.com/saksham10arora-dotcom/everything-claude-codex.git
  17. cs329z-chinese

    Docs & tutorials

    斯坦福 Stanford CS329Z Engineering AI Agents 中文教程:面向 Python 开发者的 AI 智能体课程,19 讲与 4 项实践,涵盖 LLM、RAG、工具调用、记忆、多智能体、评测与安全。完整 Markdown、在线与离线 HTML。Chinese course notes.

    Stale GitHub, wanghao-SunSky 512 ★Updated 11 days ago

    git clone https://github.com/wanghao-SunSky/cs329z-chinese.git
  18. SkillHone

    Skills

    Continual agent skill evolution through persistent decision history. Whole-skill optimisation (SKILL.md + scripts + references) with every decision landing as a local Git issue / PR / wiki. Runs on any agentskills.io runtime — Claude Code, Codex, OpenClaw, Hermes.

    Stale GitHub, Tencent 172 ★Custom licence (see repository)Updated 14 days ago

    git clone https://github.com/Tencent/SkillHone.git
  19. ruin-everything

    MCP servers

    A local Chrome runtime for browser agents. Reuse logins, run tasks in the background, handle supported verification steps, and keep submission receipts.

    Indexed GitHub, yuki4266 33 ★MITUpdated yesterday

    git clone https://github.com/yuki4266/ruin-everything.git
  20. 28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools

    Stale GitHub, tjboudreaux 1,637 ★MITUpdated 3 months ago

    git clone https://github.com/tjboudreaux/cc-thinking-skills.git
  21. kiso

    Agents & frameworks

    The durable runtime for AI agents: event-sourced sessions, approvals that persist across processes, exact resume after a crash. A 2,200-line TypeScript kernel, and kiso-code, the coding agent built on it.

    Indexed GitHub, vincemakes 96 ★MITUpdated yesterday

    git clone https://github.com/vincemakes/kiso.git
  22. hamilton

    AI repositories

    Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

    Indexed GitHub, apache 2,630 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/apache/hamilton.git
  23. lobu

    MCP servers

    Open-source control plane and runtime for organisational agents: shared company context & brain

    Indexed GitHub, lobu-ai 235 ★Apache-2.0Updated yesterday

    git clone https://github.com/lobu-ai/lobu.git
  24. Toolport

    MCP servers

    Local MCP gateway: set up servers once and share them with every AI client

    Indexed Official MCP Registry, io.github.btsouth 241 ★Updated yesterday 1 note

    ghcr.io/btsouth/toolport-gateway:v2.3.6

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.