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 that runs on your own computer and works through chats such as WhatsApp, Telegram, Slack and Discord. It can research topics, edit files, operate a browser and schedule work using enabled tools. Its background service connects chats, AI models and tools. State and credentials stay on your hardware, while configured external services receive the requests needed for their work. 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 2026-10-18

    About AI summaries

  • Context & retrievalGitHub · Repository

    ragflow

    infiniflow/ragflow

    91,802 GitHub stars
    Checked 2026-10-08 UTC

    50-WORD AI EDITORIAL SUMMARY

    RAGFlow combines retrieval-augmented generation and agent-oriented context processing. Potential use: Supply relevant context to agents while preserving provenance and access boundaries. This suggests an integration pattern; suitability depends on your tools and constraints. Before considering unattended use, check permissions and platform compatibility against your requirements in a small controlled test.

    Potential use

    Supply relevant context to agents while preserving provenance and access boundaries.

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

    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

  • Desktop executionGitHub · Repository

    cua

    trycua/cua

    29,986 GitHub stars
    Checked 2026-10-17 UTC

    50-WORD AI EDITORIAL SUMMARY

    CUA supplies computer-use drivers, cross-platform fleets and benchmarks for training and evaluation. Potential use: Connect operator tasking to tools while preserving permission boundaries. 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

    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

    9,195 GitHub stars
    Checked 2026-10-07 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

  • Runtime patternsGitHub · Repository

    loopx

    loopx-project/loopx

    6,343 GitHub stars
    Checked 2026-10-16 UTC

    50-WORD AI EDITORIAL SUMMARY

    LoopX provides durable state and a control plane for agents and teams handling extended tasks. 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. 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

  • Repository automationGitHub · Repository

    GitHub Agentic Workflows

    github/gh-aw

    5,418 GitHub stars
    Checked 2026-10-18 UTC

    AI EDITORIAL SUMMARY

    GitHub Agentic Workflows helps repository maintainers use AI agents to triage issues, investigate failed builds, review pull requests and prepare activity reports. Developers describe a task in Markdown, choose when it runs and set its tools and permissions. GitHub Actions runs the workflow with read-only GitHub access and sandboxed agent jobs by default; configured writes normally use separate validated jobs. Project guide

    GitHub activity

    5,412 stars · 593 forks · 53 watchers. Checked 2026-10-18 UTC.

    Read full summary →View source ↗
    Publication date unavailableEditorial reviewed 2026-10-18

    About AI summaries

  • Context & retrievalGitHub · Repository

    AutoRAG

    Marker-Inc-Korea/AutoRAG

    5,117 GitHub stars
    Checked 2026-10-08 UTC

    50-WORD AI EDITORIAL SUMMARY

    AutoRAG explores retrieval-augmented search agents with learning-oriented workflows. Potential use: Supply relevant context to agents while preserving provenance and access boundaries. This suggests an integration pattern; suitability depends on your tools and constraints. Before considering unattended use, check permissions and platform compatibility against your requirements in a small controlled test.

    Potential use

    Supply relevant context to agents while preserving provenance and access boundaries.

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

    About AI summaries

  • Desktop executionGitHub · Repository

    Chat On Steroids

    totec448-spec/chat-on-steroids

    5,003 GitHub stars
    Checked 2026-10-17 UTC

    50-WORD AI EDITORIAL SUMMARY

    Chat On Steroids connects ChatGPT conversations with local files, terminals and desktop tools through MCP. Its workers and session continuation features support longer delegated tasks. For agentic development, it illustrates coordination between an operator, conversation and execution tools. It is an independent beta; permissions and provider rules require careful review.

    Potential use

    Connect conversational tasking with local tools and delegated work.

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

    About AI summaries

  • Reference & discoveryGitHub · Repository

    awesome-opensource-ai

    alvinreal/awesome-opensource-ai

    4,843 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    Awesome OpenSource AI collects models, tools and infrastructure projects for discovery and comparison. 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

    arcbox

    arcboxlabs/arcbox

    4,223 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    Arcbox provides isolated agent machines with separate kernels, filesystems and networks, using local infrastructure. 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

  • Desktop executionGitHub · Repository

    dsh-TUI

    ccch1mneyyy/dsh-TUI

    4,147 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    DSH TUI provides a terminal interface plugin for DeepSeek Harness with mouse interaction. Potential use: Connect operator tasking to tools while preserving permission boundaries. 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 operator tasking to tools while preserving permission boundaries.

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

    About AI summaries

  • Runtime patternsGitHub · Repository

    fast-agent

    evalstate/fast-agent

    3,928 GitHub stars
    Checked 2026-10-10 UTC

    50-WORD AI EDITORIAL SUMMARY

    Fast-Agent supports building and evaluating agents with models, skills and multiple agent interoperability protocols. 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

  • Runtime patternsGitHub · Repository

    tract

    sonos/tract

    3,081 GitHub stars
    Checked 2026-10-08 UTC

    50-WORD AI EDITORIAL SUMMARY

    Tract provides self-contained inference for TensorFlow and ONNX models as an application building block. 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

  • Task orchestrationGitHub · Repository

    agent-teams-ai

    777genius/agent-teams-ai

    2,236 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    Agent Teams AI organizes multiple agents with task boards, handoffs and review steps across providers. Potential use: Coordinate task handoffs with explicit responsibilities and review points. 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

    Coordinate task handoffs with explicit responsibilities and review points.

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

    About AI summaries