InnerVault

Library

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

Results

757 results with any of your words Clear search and filters

Looks like a goal we have a starting path for: I want to research potential clients

  1. imp

    Agents & frameworks

    Run large AI chat models privately on your own NVIDIA RTX 50 or RTX PRO graphics card. On one RTX 5090, Qwen3.8-27B writes about 70 words per second, 1.4x faster than vLLM. Even a model almost four times larger than the card's memory runs. Works with apps made for ChatGPT or Claude. Starts with one docker command.

    Stale GitHub, kekzl 124 ★MITUpdated 13 days ago

    git clone https://github.com/kekzl/imp.git
  2. otto-cognitive-nudge

    Agents & frameworks

    Smart Promise Tracker AI 2026 – Commit Memory Engine

    Indexed GitHub, muhammadalicusit56-glitch 142 ★Updated yesterday

    git clone https://github.com/muhammadalicusit56-glitch/otto-cognitive-nudge.git
  3. ClaudeCode-Workflow-Lab

    Agents & frameworks

    Complete Guide 2026: Claude Code Manual – Workflow Pipelines & Adversarial Budget Loops

    Indexed GitHub, Frisher1 116 ★Updated yesterday

    git clone https://github.com/Frisher1/ClaudeCode-Workflow-Lab.git
  4. awesome-auditable-ai

    Agents & frameworks

    Auditing AI agents: a curated list of papers, tools, datasets, benchmarks, and standards covering reliability, monitoring, failure attribution, and decision records.

    Stale GitHub, yzhao062 154 ★CC0-1.0Updated 29 days ago

    git clone https://github.com/yzhao062/awesome-auditable-ai.git
  5. RSI-Jev

    Agents & frameworks

    Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.

    Indexed GitHub, Shanghua-Gao 137 ★MITUpdated yesterday

    git clone https://github.com/Shanghua-Gao/RSI-Jev.git
  6. awaken

    Agents & frameworks

    AI agent runtime for Rust — type-safe state, multi-protocol serving, plugin extensibility.

    Indexed GitHub, awakenworks 101 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/awakenworks/awaken.git
  7. symfony-security-auditor

    Agents & frameworks

    AI-powered multi-agent security auditor for Symfony applications, provider-agnostic via symfony/ai.

    Stale GitHub, vinceAmstoutz 100 ★MITUpdated 19 days ago

    git clone https://github.com/vinceAmstoutz/symfony-security-auditor.git
  8. NEWTON

    Agents & frameworks

    NEWTON: Agentic Planning for Physically Grounded Video Generation

    Stale GitHub, CUTEPKQ 139 ★MITUpdated 3 months ago

    git clone https://github.com/CUTEPKQ/NEWTON.git
  9. codex-source-analysis

    Agents & frameworks

    OpenAI Codex 源码深度研究 (Rust + TS + Python):2 总纲 + 25 章 + 3 附录, ~51 万字 + 149 张 Mermaid 架构图

    Stale GitHub, xiaonancs 117 ★Custom licence (see repository)Updated 5 months ago

    git clone https://github.com/xiaonancs/codex-source-analysis.git
  10. AI-Interview

    Agents & frameworks

    开源的 AI 模拟面试系统:真人数字人面试官开口提问、按你的回答追问,报告逐题打分;另含 Docker 判题笔试与 AI 简历优化。Java 21 + Spring AI Alibaba + Vue 3。

    Stale GitHub, xgwangdl 234 ★Apache-2.0Updated 29 days ago

    git clone https://github.com/xgwangdl/AI-Interview.git
  11. MulmoChat

    Agents & frameworks

    Research prototype for chat that is not a text stream: keep talking while images, maps and playable games appear on the canvas. Each kind of answer is a plugin on the GUI Chat Protocol.

    Indexed GitHub, receptron 178 ★MITUpdated yesterday

    git clone https://github.com/receptron/MulmoChat.git
  12. mancode

    Agents & frameworks

    AI coding agent harness. Five modes: practice to playoffs. Stop your AI from over-engineering. Code like a man. Elbow out bloat. Score clean. ... AI 代理调度框架。五种模式:训练到季后赛。 别让你的 AI 过度设计一切。像个man一样,肘开冗余,干净得分。

    Stale GitHub, whitelonng 359 ★AGPL-3.0Updated 23 days ago

    git clone https://github.com/whitelonng/mancode.git
  13. zenflow

    Agents & frameworks

    Multi-agent orchestration & workflow engine. Declarative YAML workflows, LLM coordinator with hub-and-spoke mailboxes, race-safe delivery. One YAML file, one Go binary. Runs on any goai-supported provider.

    Stale GitHub, zendev-sh 57 ★Apache-2.0Updated 15 days ago

    git clone https://github.com/zendev-sh/zenflow.git
  14. HARTOS

    Agents & frameworks

    An AI-native OS. Models run on your own hardware, nodes federate peer-to-peer with no broker, and the API is OpenAI-compatible. Boots, has its own Wayland compositor, and runs on 8GB. Apache 2.0.

    Indexed GitHub, hertz-ai 52 ★Apache-2.0Updated yesterday

    git clone https://github.com/hertz-ai/HARTOS.git
  15. OpenGUI

    Agents & frameworks

    Open-source desktop and web coding agent with a first-party host and harness, durable sessions, model connections, streaming chat, and workspace tools.

    Stale GitHub, akemmanuel 117 ★MITUpdated 22 days ago

    git clone https://github.com/akemmanuel/OpenGUI.git
  16. WEIPING_WHALE

    Agents & frameworks

    A small terminal coding agent for DeepSeek models: it reads your repository, runs commands after asking, proposes edits as patches you apply, and checkpoints the workspace around every turn so any turn can be undone.

    Stale GitHub, appleweiping 131 ★MITUpdated 23 days ago

    git clone https://github.com/appleweiping/WEIPING_WHALE.git
  17. bloks

    Agents & frameworks

    A local-first desktop app for running a team of AI agents on Claude Code, Codex, Cursor, Cline and more, on your own computer.

    Stale GitHub, hamedgitty 315 ★Custom licence (see repository)Updated 5 days ago

    git clone https://github.com/hamedgitty/bloks.git
  18. agentglass

    Agents & frameworks

    🛰 Every AI coding agent on your machine, on one screen — live cost, tokens and tool calls across every provider, and a hold on anything dangerous until you say go. From your desk or your phone.

    Stale GitHub, SirAllap 343 ★MITUpdated 23 days ago

    git clone https://github.com/SirAllap/agentglass.git
  19. forest

    Agents & frameworks

    FOREST is a research agent for long-horizon science, where evidence gets lost, errors compound, and goals drift. It explores ideas, reads literature, forms hypotheses, runs real experiments, analyzes results, revises paths, and builds a full paper—all in an editable graph you can inspect, branch, redirect, with claims and figures linked to evidence

    Stale GitHub, mikamikasuki 355 ★Apache-2.0Updated 21 days ago

    git clone https://github.com/mikamikasuki/forest.git
  20. Abu-Cowork

    Agents & frameworks

    Open-source AI office assistant for your desktop: describe the result or file you want in one sentence, and Abu plans and does the rest. Local-first, with Claude, OpenAI, DeepSeek and Ollama.

    Indexed GitHub, PM-Shawn 421 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/PM-Shawn/Abu-Cowork.git
  21. EDAgent

    Agents & frameworks

    Multi-agent exploratory data analysis system with autonomous insights, visualization, preprocessing, and reporting workflows.

    Stale GitHub, Varn1t 50 ★Updated 16 days ago

    git clone https://github.com/Varn1t/EDAgent.git
  22. Jixu

    Agents & frameworks

    Durable single-Agent Harness for TypeScript: recoverable Threads, context continuity, explicit side effects, and a native TUI.

    Stale GitHub, joe960913 93 ★MITUpdated 48 days ago

    git clone https://github.com/joe960913/Jixu.git
  23. AnvilWiki

    Agents & frameworks

    ⚒️ Open-source game wiki template. Astro + Cloudflare Pages. Free, fast, beginner-friendly. Static-first, zero-JS, AI-native content workflow, unlimited bandwidth.

    Stale GitHub, PNGTRID 212 ★MITUpdated 15 days ago

    git clone https://github.com/PNGTRID/AnvilWiki.git
  24. FinSight

    Agents & frameworks

    Multi-agent会话式金融研究平台。提供专业智能体(价格分析、新闻追踪、宏观经济、深度研究),支持实时流式响应、自动生成8章节投资报告和投资组合监控。采用LangGraph、FastAPI和React技术栈开发。

    Indexed GitHub, kkkano 63 ★MITUpdated 2 days ago

    git clone https://github.com/kkkano/FinSight.git

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.