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 2

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

Loading your favourites…

  • Perception toolingGitHub · Repository

    video-search-and-summarization

    NVIDIA-AI-Blueprints/video-search-and-summarization

    1,911 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    Video Search and Summarization combines GPU video analytics, visual questions, alerts and reporting workflows. 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 using 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

  • Planning algorithmsGitHub · Repository

    timefold-solver

    TimefoldAI/timefold-solver

    1,813 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    Timefold Solver optimizes scheduling, routing and assignment problems in Java and Kotlin. Potential use: Combine constraint-based planning with agent tasking rather than relying on language alone. 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

    Combine constraint-based planning with agent tasking rather than relying on language alone.

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

    About AI summaries

  • Tool integrationGitHub · Repository

    pi-mcp-adapter

    nicobailon/pi-mcp-adapter

    1,583 GitHub stars
    Checked 2026-10-09 UTC

    50-WORD AI EDITORIAL SUMMARY

    Pi MCP Adapter connects Pi agents to MCP tools with attention to tool-description overhead. 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

  • Task orchestrationGitHub · Repository

    agentconnect

    agentconnect-md/agentconnect

    1,471 GitHub stars
    Checked 2026-10-17 UTC

    50-WORD AI EDITORIAL SUMMARY

    AgentConnect supports team collaboration by directing messages and tasks to named agents. 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

  • Task orchestrationGitHub · Repository

    alook

    alookai/alook

    1,420 GitHub stars
    Checked 2026-10-18 UTC

    50-WORD AI EDITORIAL SUMMARY

    Alook gives local coding agents persistent identities and shared rooms where trusted people can collaborate. 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

  • Applied workflowsGitHub · Repository

    mirobody

    thetahealth/mirobody

    1,361 GitHub stars
    Checked 2026-10-08 UTC

    50-WORD AI EDITORIAL SUMMARY

    Mirobody connects health datasets and wearable information with self-hosted AI reporting and MCP tools. Potential use: Study a concrete application pattern before adapting it to another workflow. 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 a concrete application pattern before adapting it to another workflow.

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

    About AI summaries

  • Agent workspacesGitHub · Repository

    OpenHarness

    autonomous-ai/openharness

    1,295 GitHub stars
    Checked 2026-10-18 UTC

    AI EDITORIAL SUMMARY

    OpenHarness is a workspace for supervising coding agents on your computers and servers. Its macOS and Linux app brings their conversations, terminals and projects together so you can find work waiting for your answer and keep changes on separate branches. Optional specialist packages connect agents to tools and live viewers for design, circuit simulation, robotics, games and documents. Work continues while its host remains running. Project guide

    GitHub activity

    1,295 stars · 112 forks · 2 watchers. Checked 2026-10-18 UTC.

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

    About AI summaries

  • Tool integrationGitHub · Repository

    anythingmcp

    HelpCode-ai/anythingmcp

    980 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    AnythingMCP adapts business APIs into MCP tools through a self-hosted gateway. 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 platform compatibility 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

  • Context & retrievalGitHub · Repository

    hippo-memory

    kitfunso/hippo-memory

    773 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    Hippo Memory stores longer-term coding-agent context locally and connects memory across development tools. 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 adoption, check permissions 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

  • Runtime patternsGitHub · Repository

    agentos

    framerslab/agentos

    677 GitHub stars
    Checked 2026-10-12 UTC

    50-WORD AI EDITORIAL SUMMARY

    AgentOS offers a TypeScript agent framework with memory, tool construction and multi-agent coordination. 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.

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

    About AI summaries

  • Desktop executionGitHub · Repository

    openbot

    nightly-labs/openbot

    580 GitHub stars
    Checked 2026-10-16 UTC

    50-WORD AI EDITORIAL SUMMARY

    OpenBot provides persistent desktop agent workspaces with task queues, files, browser tools and collaboration. 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

  • Evaluation & controlsGitHub · Repository

    SkillEvaluator

    NVIDIA/SkillEvaluator

    575 GitHub stars
    Checked 2026-10-18 UTC

    50-WORD AI EDITORIAL SUMMARY

    SkillEvaluator evaluates agent skills using quality gates, semantic-overlap checks, generated datasets and evaluation workflows. Potential use: Use measured evidence to distinguish completed work from unsupported agent claims. 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

    Use measured evidence to distinguish completed work from unsupported agent claims.

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

    About AI summaries

  • Task orchestrationGitHub · Repository

    smithers

    smithersai/smithers

    431 GitHub stars
    Checked 2026-10-10 UTC

    50-WORD AI EDITORIAL SUMMARY

    Smithers defines agent workflows in TypeScript configuration with durable execution support. 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 permissions and licensing 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

  • Desktop executionGitHub · Repository

    peerd

    NotASithLord/peerd

    417 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    PeerD runs an agent loop in a browser extension with tab tools, notebooks and sandboxed computation. 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 using 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

    useagent

    useagenthq/useagent

    368 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    UseAgent provides self-hosted coding workspaces with isolated execution environments and multiple agent choices. 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

  • Desktop executionGitHub · Repository

    agentrove

    Mng-dev-ai/agentrove

    336 GitHub stars
    Checked 2026-10-10 UTC

    50-WORD AI EDITORIAL SUMMARY

    Agentrove provides a self-hosted coding workspace with multiple agent personas and sandboxed agent sessions. 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

    nanoMuse

    nano-muse/nanoMuse

    334 GitHub stars
    Checked 2026-10-08 UTC

    50-WORD AI EDITORIAL SUMMARY

    NanoMuse presents a personal agent across devices with continued work, memory and confirmation for consequential actions. 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 using 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

    Cotal

    Cotal-AI/Cotal

    312 GitHub stars
    Checked 2026-10-08 UTC

    50-WORD AI EDITORIAL SUMMARY

    Cotal proposes a coordination standard for agents working together across tasks. 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 permissions and licensing 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

    mecatl

    stacklok/mecatl

    248 GitHub stars
    Checked 2026-10-08 UTC

    50-WORD AI EDITORIAL SUMMARY

    Mecatl provides a provider-neutral agent harness with durable state, permissions and local or remote execution interfaces. 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 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

    mulmoterminal

    receptron/mulmoterminal

    236 GitHub stars
    Checked 2026-10-07 UTC

    50-WORD AI EDITORIAL SUMMARY

    MulmoTerminal shows parallel coding-agent sessions in a local browser terminal grid backed by tmux. 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

  • Runtime patternsGitHub · Repository

    limen

    overment/limen

    231 GitHub stars
    Checked 2026-10-18 UTC

    50-WORD AI EDITORIAL SUMMARY

    Limen is an agent harness organized around files, Git and command-line tools for coordinating multiple agents. 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 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