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

Trending

50 on this page · Page 5

Observed GitHub star growth per day, comparing saved observations about a week apart. Each card shows the actual dates. Counts describe attention, not quality.

Loading your favourites…

  • Reference & discoveryGitHub · Repository

    CoursIA

    jsboige/CoursIA

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    CoursIA provides AI course materials and practical examples using C# and Python. 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 platform compatibility 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

  • Desktop executionGitHub · Repository

    ghost-os

    Judaca73/ghost-os

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Ghost OS exposes macOS application interaction, including clicking, form entry and messaging operations. 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

    abi

    jupyter-naas/abi

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    ABI presents an open AI operating-system project as a foundation for agent 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 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

  • Context & retrievalGitHub · Repository

    hippo-memory

    kitfunso/hippo-memory

    Insufficient recent history

    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

  • Evaluation & controlsGitHub · Repository

    runtune

    kkrlstrm/runtune

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    RunTune proposes measured harness changes involving rules, skills and routing, subject to human approval. 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

  • Context & retrievalGitHub · Repository

    data-olympus

    knaisoma/data-olympus

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Data Olympus proposes a governed knowledge format with single-writer MCP and command-line access. 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

  • Desktop executionGitHub · Repository

    juno

    lacymorrow/juno

    Insufficient recent history

    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.

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

    About AI summaries

  • Desktop executionGitHub · Repository

    sleight

    Land-o-Clusters/sleight

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Sleight supplies a computer-use engine for agents interacting with background macOS applications. 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

  • Desktop executionGitHub · Repository

    spyhop

    leeleelee3264/spyhop

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Spyhop provides a local status board for Claude Code and Codex sessions running in Orca. 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

  • Context & retrievalGitHub · Repository

    deeprecall

    leo2007960216/deeprecall

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    DeepRecall explores recursive retrieval and language-model reasoning over external information. 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 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

  • Tool integrationGitHub · Repository

    trajan

    Lideeyah/trajan

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Trajan connects seller workflows and payment-related APIs through MCP and supporting interfaces. 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

  • Evaluation & controlsGitHub · Repository

    agent-evaluation-framework

    Lin-chpin/agent-evaluation-framework

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Agent Evaluation Framework provides pluggable evaluation for agents and skills with auditable, reversible improvement processes. 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. Check permissions against your requirements in 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

  • Reference & discoveryGitHub · Repository

    agent-framework-radar

    linny006/agent-framework-radar

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Agent Framework Radar indexes recently active agent frameworks to support discovery beyond popularity rankings. 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 integrating it, 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

  • Reference & discoveryGitHub · Repository

    claude-code-plugin-tracker

    linny006/claude-code-plugin-tracker

    Insufficient recent history

    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.

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

    About AI summaries

  • Reference & discoveryGitHub · Repository

    rag-radar

    linny006/rag-radar

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    RAG Radar tracks retrieval implementations, tools and patterns as a discovery resource. 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 platform compatibility 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

  • Reference & discoveryGitHub · Repository

    trending-claude-skills

    linny006/trending-claude-skills

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Trending Claude Skills tracks skill repositories as a discovery resource for coding-agent capabilities. 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

  • Task orchestrationGitHub · Repository

    lobu

    lobu-ai/lobu

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Lobu combines an organizational agent control plane, runtime and shared context. 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

    vibeweaver

    logandoo/vibeweaver

    Insufficient recent history

    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.

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

    About AI summaries

  • Runtime patternsGitHub · Repository

    loopx

    loopx-project/loopx

    Insufficient recent history

    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

  • Runtime patternsGitHub · Repository

    gokin-sdk

    Luiz184/gokin-sdk

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Gokin SDK supplies Go components for multi-agent planning, tool use and several hosted or local model providers. 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.

    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

    multi-agent-collaboration

    lzhs1995/multi-agent-collaboration

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Multi Agent Collaboration coordinates Codex and Claude sessions using bounded recovery, callbacks and execution evidence. 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

  • Runtime patternsGitHub · Repository

    harness

    majorcontext/harness

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    MajorContext Harness supplies composable Go components for constructing agent execution harnesses. 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 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

  • Evaluation & controlsGitHub · Repository

    rag-telemetry-evals

    Manojkumarcherukuneedi/rag-telemetry-evals

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    RAG Telemetry Evals combines retrieval telemetry, citations and evaluation checks in continuous integration. 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 adoption, check permissions against your requirements in 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