AI IntelligencePUBLIC DISCOVERIES

IDEAS FOR AGENTIC DEVELOPMENT

Discover it.
Understand its value.

Saved public GitHub discoveries, explained in 50 words. 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 10

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

Loading your favourites…

  • Desktop executionGitHub · Repository

    cli

    inference-gateway/cli

    7 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    Inference Gateway CLI combines Git-oriented coding tasks with remote control and computer automation. 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.

  • Desktop executionGitHub · Repository

    juno

    lacymorrow/juno

    7 GitHub stars
    Checked 2026-10-08 UTC

    50-WORD AI EDITORIAL SUMMARY

    Juno provides a native macOS application for agent-driven computer 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 and platform compatibility against your requirements in a small controlled test.

    Potential use

    Connect operator tasking to tools while preserving permission boundaries.

  • Task orchestrationGitHub · Repository

    agent-workflow

    ZibbyDev/agent-workflow

    7 GitHub stars
    Checked 2026-10-08 UTC

    50-WORD AI EDITORIAL SUMMARY

    Agent Workflow composes coding agents as graphs with schema-defined handoffs between steps. 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.

  • Desktop executionGitHub · Repository

    longhouse

    cipher982/longhouse

    6 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    Longhouse provides remote control of coding-agent sessions across supported providers. 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 and platform compatibility against your requirements in a small controlled test.

    Potential use

    Connect operator tasking to tools while preserving permission boundaries.

  • Reference & discoveryGitHub · Repository

    claude-code-plugin-tracker

    linny006/claude-code-plugin-tracker

    6 GitHub stars
    Checked 2026-10-20 UTC

    50-WORD AI EDITORIAL SUMMARY

    Claude Code Plugin Tracker indexes plugins, hooks and extensions for Claude Code workflows. 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.

  • Runtime patternsGitHub · Repository

    vibeweaver

    logandoo/vibeweaver

    6 GitHub stars
    Checked 2026-10-19 UTC

    50-WORD AI EDITORIAL SUMMARY

    VibeWeaver organizes agent workflows as bounded graph state machines with explicit gates and benchmarks. 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.

  • Runtime patternsGitHub · Repository

    milk

    scoutme/milk

    6 GitHub stars
    Checked 2026-10-10 UTC

    50-WORD AI EDITORIAL SUMMARY

    Milk coordinates terminal agents, transferring context from a primary worker to specialist models. 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 adoption, check permissions against your requirements in a small controlled test.

    Potential use

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

  • Tool integrationGitHub · Repository

    Skeepto

    Stephane-76/Skeepto

    6 GitHub stars
    Checked 2026-10-08 UTC

    50-WORD AI EDITORIAL SUMMARY

    Skeepto provides a C++ spreadsheet engine compiled to WebAssembly with browser and Node 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.

  • Context & retrievalGitHub · Repository

    rag-document-intelligence

    unamerican-bias763/rag-document-intelligence

    6 GitHub stars
    Checked 2026-10-08 UTC

    50-WORD AI EDITORIAL SUMMARY

    RAG Document Intelligence combines local retrieval and OCR for scanned documents and structured information extraction. 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. Check permissions against your requirements in a small controlled test.

    Potential use

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