AI IntelligencePUBLIC DISCOVERIES

IDEAS FOR AGENTIC DEVELOPMENT

Discover it.
Understand its value.

Saved public GitHub discoveries, explained in short summaries. Explore what each project does and how it could help you build, coordinate or evaluate agents.

Explore the feed ↓

EXPLORE THE FEED

Popular

50 on this page · Page 1

Projects ordered by their latest saved GitHub star count. Counts describe public interest, not quality. Check the dates on each card.

Loading your favourites…

  • Personal and team assistantsGitHub · Repository

    OpenClaw

    openclaw/openclaw

    392,286 GitHub stars
    Checked 2026-10-18 UTC

    AI EDITORIAL SUMMARY

    OpenClaw is an open-source AI assistant you run on your own computer. You can give it jobs through chat apps such as WhatsApp, Telegram, Slack and Discord. With the right tools enabled, it can research topics, edit files, use a browser and run tasks at set times. Project guide

    GitHub activity

    392,286 stars · 82,459 forks · 1,708 watchers. Checked 2026-10-18 UTC.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-30

    About AI summaries

  • Developer toolGitHub · Repository

    REA

    morluto/rea

    342,880 GitHub stars
    Checked 2026-10-20 UTC

    AI EDITORIAL SUMMARY

    REA helps an AI coding assistant investigate how a program works when its source code is missing. It connects the assistant to tools that inspect apps, program files and websites, and can collect evidence for its findings. It is most relevant to developers doing software maintenance, compatibility work or security research. Project guide

    GitHub activity

    410,160 stars · 102,666 forks · 1,565 watchers. Checked 2026-10-30 UTC.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-31

    About AI summaries

  • Agent platformGitHub · Repository

    AutoGPT

    Significant-Gravitas/AutoGPT

    187,649 GitHub stars
    Checked 2026-10-19 UTC

    AI EDITORIAL SUMMARY

    AutoGPT helps people give recurring business jobs to AI assistants with defined roles. Its current product offers a coordinator called Otto and specialists for work such as research, content briefs and meeting preparation. You can review their output and connect the accounts they need. Hosted and self-hosted options have different setup and usage requirements. Project guide

    GitHub activity

    187,825 stars · 45,900 forks · 1,531 watchers. Checked 2026-10-30 UTC.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-31

    About AI summaries

  • Agent platformGitHub · Repository

    Dify

    langgenius/dify

    159,016 GitHub stars
    Checked 2026-10-20 UTC

    AI EDITORIAL SUMMARY

    Dify lets teams build AI apps by connecting steps on a visual canvas. An app can answer questions from documents, call configured tools and pass work between AI models and other services. It can be shared as a web app or called from your own software. The result still needs checking against the source material. Project guide

    GitHub activity

    159,985 stars · 25,278 forks · 840 watchers. Checked 2026-10-30 UTC.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-31

    About AI summaries

  • Agent managementGitHub · Repository

    Paperclip

    paperclipai/paperclip

    103,091 GitHub stars
    Checked 2026-10-16 UTC

    AI EDITORIAL SUMMARY

    Paperclip gives people one place to assign work to AI agents, follow progress and review the results. It organises tasks, roles, permissions and reported spending in a dashboard. You bring the agents and their AI access. It is most useful when several agents or recurring jobs have become difficult to manage separately. Project guide

    GitHub activity

    108,830 stars · 18,016 forks · 480 watchers. Checked 2026-10-30 UTC.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-31

    About AI summaries

  • Agent memoryGitHub · Repository

    Claude-Mem

    thedotmack/claude-mem

    101,372 GitHub stars
    Checked 2026-10-17 UTC

    AI EDITORIAL SUMMARY

    Claude-Mem helps an AI coding assistant carry useful information from one work session into the next. It captures activity, turns it into searchable notes and supplies relevant context later. A developer could use it to recover earlier decisions or debugging history. Storage, AI processing and optional cloud features need separate privacy and cost checks. Project guide

    GitHub activity

    105,311 stars · 9,285 forks · 322 watchers. Checked 2026-10-30 UTC.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-31

    About AI summaries

  • Developer workspaceGitHub · Repository

    Orca

    stablyai/orca

    96,349 GitHub stars
    Checked 2026-10-18 UTC

    AI EDITORIAL SUMMARY

    Orca puts AI coding sessions, terminals, code changes and browser previews in one workspace. Developers can give agents separate working copies of a project, review their changes and steer work from a paired phone. It works with existing coding agents, so the agents’ subscriptions, permissions and output quality remain part of the setup. Project guide

    GitHub activity

    110,646 stars · 6,992 forks · 148 watchers. Checked 2026-10-30 UTC.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-31

    About AI summaries

  • Document intelligenceGitHub · Repository

    RAGFlow

    infiniflow/ragflow

    92,459 GitHub stars
    Checked 2026-10-19 UTC

    AI EDITORIAL SUMMARY

    RAGFlow helps teams turn a collection of documents into a searchable source for AI answers. It parses files, finds relevant passages and can show citations alongside a response. Developers can connect it to an app or agent workflow. Readers still need to check that the cited material actually supports the answer. Project guide

    GitHub activity

    93,178 stars · 11,178 forks · 358 watchers. Checked 2026-10-30 UTC.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-31

    About AI summaries

  • Developer workspaceGitHub · Repository

    OpenHands

    OpenHands/OpenHands

    91,355 GitHub stars
    Checked 2026-10-20 UTC

    AI EDITORIAL SUMMARY

    OpenHands’ Agent Canvas gives developers a browser workspace for coding agents and recurring engineering jobs. It brings conversations, files, terminals and agent backends together, and can connect work to services such as GitHub and Slack. Agents can run locally or in other environments. Their file access and isolation depend on the chosen setup. Project guide

    GitHub activity

    92,253 stars · 12,270 forks · 496 watchers. Checked 2026-10-30 UTC.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-31

    About AI summaries

  • Agent coordinationGitHub · Repository

    Ruflo

    ruvnet/ruflo

    77,525 GitHub stars
    Checked 2026-10-20 UTC

    AI EDITORIAL SUMMARY

    Ruflo adds tools, shared project memory and coordination features around AI coding agents such as Claude Code and Codex. Developers can use it to organise related jobs and inspect progress through supported clients or a console. The available controls depend on the integration. Running more agents does not by itself produce better work or lower costs. Project guide

    GitHub activity

    80,226 stars · 9,408 forks · 475 watchers. Checked 2026-10-30 UTC.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-31

    About AI summaries

  • Agent memoryGitHub · Repository

    Hindsight

    vectorize-io/hindsight

    51,453 GitHub stars
    Checked 2026-10-19 UTC

    AI EDITORIAL SUMMARY

    Hindsight gives AI applications a place to store useful information from earlier interactions and retrieve it later. It can extract facts, search memories and use them to prepare a response. Developers connect it to an existing agent or app. Check that a recalled fact is current and belongs to the person or project using it. Project guide

    GitHub activity

    56,383 stars · 6,747 forks · 113 watchers. Checked 2026-10-30 UTC.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-31

    About AI summaries

  • Desktop executionGitHub · Repository

    invisible_dots

    feder-cr/invisible_dots

    31,805 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    Invisible Dots presents self-hosted computer automation; its claims about avoiding detection require particular scrutiny. Potential use: Connect operator tasking to tools while preserving permission boundaries. This suggests an integration pattern; suitability depends on your tools and constraints. Before integrating it, check permissions against your requirements in a small controlled test.

    Potential use

    Connect operator tasking to tools while preserving permission boundaries.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-11

    About AI summaries

  • Task orchestrationGitHub · Repository

    sim

    simstudioai/sim

    29,792 GitHub stars
    Checked 2026-10-08 UTC

    50-WORD AI EDITORIAL SUMMARY

    Sim supports collaborative creation, deployment and monitoring of agents and automated workflows. Potential use: Coordinate task handoffs with explicit responsibilities and review points. This suggests an integration pattern; suitability depends on your tools and constraints. Before considering unattended use, check platform compatibility against your requirements in a small controlled test.

    Potential use

    Coordinate task handoffs with explicit responsibilities and review points.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-11

    About AI summaries

  • Runtime patternsGitHub · Repository

    adk-python

    google/adk-python

    21,735 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    Google ADK supplies a Python framework for building, evaluating and deploying agents through code. Potential use: Study execution loops and state handling before designing an agent runtime. This suggests an integration pattern; suitability depends on your tools and constraints. Before considering unattended use, check permissions using a small controlled test.

    Potential use

    Study execution loops and state handling before designing an agent runtime.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-11

    About AI summaries

  • Perception toolingGitHub · Repository

    kornia

    kornia/kornia

    11,432 GitHub stars
    Checked 2026-10-17 UTC

    50-WORD AI EDITORIAL SUMMARY

    Kornia supplies geometric computer-vision components for spatial AI and image-processing pipelines. Potential use: Provide visual evidence to agent workflows without assuming perception is reliable. This suggests an integration pattern; suitability depends on your tools and constraints. Before considering unattended use, check permissions against your requirements in a small controlled test.

    Potential use

    Provide visual evidence to agent workflows without assuming perception is reliable.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-11

    About AI summaries

  • Desktop executionGitHub · Repository

    ekko-studio

    EKKOLearnAI/ekko-studio

    11,330 GitHub stars
    Checked 2026-10-08 UTC

    50-WORD AI EDITORIAL SUMMARY

    Ekko Studio combines local agent chat, coding and visual workflows in desktop and web interfaces. Potential use: Connect operator tasking to tools while preserving permission boundaries. This suggests an integration pattern; suitability depends on your tools and constraints. Before adoption, check permissions against your requirements in a small controlled test.

    Potential use

    Connect operator tasking to tools while preserving permission boundaries.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-11

    About AI summaries

  • Reference & discoveryGitHub · Repository

    ccf-deadlines

    ccfddl/ccf-deadlines

    9,413 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    CCF Deadlines tracks conference deadlines through a website, Python CLI and WeChat interface. Potential use: Compare documented approaches before choosing components for agent-assisted development. This suggests an integration pattern; suitability depends on your tools and constraints. Before considering unattended use, check permissions against your requirements in a small controlled test.

    Potential use

    Compare documented approaches before choosing components for agent-assisted development.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-11

    About AI summaries

  • Runtime patternsGitHub · Repository

    PraisonAI

    MervinPraison/PraisonAI

    9,270 GitHub stars
    Checked 2026-10-19 UTC

    50-WORD AI EDITORIAL SUMMARY

    PraisonAI combines task planning, coding, memory and retrieval in a multi-agent framework. Potential use: Study execution loops and state handling before designing an agent runtime. This suggests an integration pattern; suitability depends on your tools and constraints. Before integrating it, check permissions against your requirements in a small controlled test.

    Potential use

    Study execution loops and state handling before designing an agent runtime.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-11

    About AI summaries

  • Runtime patternsGitHub · Repository

    rig

    0xPlaygrounds/rig

    8,820 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    Rig supplies modular Rust components for building language-model applications. Potential use: Study execution loops and state handling before designing an agent runtime. This suggests an integration pattern; suitability depends on your tools and constraints. Before considering unattended use, check permissions and licensing against your requirements in a small controlled test.

    Potential use

    Study execution loops and state handling before designing an agent runtime.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-11

    About AI summaries

  • Tool integrationGitHub · Repository

    webiny-js

    webiny/webiny-js

    8,048 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    Webiny supplies a self-hosted AWS content-management platform with APIs, lifecycle hooks and MCP integration. Potential use: Connect existing software capabilities to agent tools through explicit interfaces. This suggests an integration pattern; suitability depends on your tools and constraints. Before adoption, check permissions against your requirements in a small controlled test.

    Potential use

    Connect existing software capabilities to agent tools through explicit interfaces.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-11

    About AI summaries

  • Tool integrationGitHub · Repository

    repowise

    repowise-dev/repowise

    7,203 GitHub stars
    Checked 2026-10-08 UTC

    50-WORD AI EDITORIAL SUMMARY

    RepoWise exposes code health, documentation, Git analytics and architecture information through MCP. Potential use: Connect existing software capabilities to agent tools through explicit interfaces. This suggests an integration pattern; suitability depends on your tools and constraints. Before considering unattended use, check permissions against your requirements in a small controlled test.

    Potential use

    Connect existing software capabilities to agent tools through explicit interfaces.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-11

    About AI summaries