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

Trending

50 on this page · Page 1

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…

  • Personal and team assistantsGitHub · Repository

    OpenClaw

    openclaw/openclaw

    +553 stars · 96.5/day
    2026-10-12–2026-10-18 UTC · 5.7 days

    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

  • Agent workspacesGitHub · Repository

    OpenHarness

    autonomous-ai/openharness

    +76 stars · 10.4/day
    2026-10-10–2026-10-18 UTC · 7.3 days

    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

  • Repository automationGitHub · Repository

    GitHub Agentic Workflows

    github/gh-aw

    +35 stars · 4.8/day
    2026-10-10–2026-10-18 UTC · 7.3 days

    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

  • Perception toolingGitHub · Repository

    kornia

    kornia/kornia

    +31 stars · 3.1/day
    2026-10-07–2026-10-17 UTC · 9.9 days

    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

  • Workflow executionGitHub · Repository

    Q-Core

    0design/Q-Core

    +0 stars · 0.0/day
    2026-10-10–2026-10-18 UTC · 7.3 days

    AI EDITORIAL SUMMARY

    Q-Core runs repeatable workflows on your computer with checks and human approval before controlled changes. It is the engine behind QFactory's workflow templates and works with coding agents such as Claude Code, Codex and Cursor. Templates cover agreed code changes, Ukrainian news digests and podcast summaries, and JSON transfers between services. AI model steps follow defined checks and stop conditions. Project guide

    GitHub activity

    4 stars · 2 forks · 0 watchers. Checked 2026-10-18 UTC.

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

    About AI summaries

  • Runtime patternsGitHub · Repository

    rig

    0xPlaygrounds/rig

    Insufficient recent history

    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

  • Reference & discoveryGitHub · Repository

    rag-from-scratch

    1green9code9ondas9/rag-from-scratch

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    RAG From Scratch teaches retrieval-augmented generation using external context and worked implementation examples. 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

    agent-teams-ai

    777genius/agent-teams-ai

    Insufficient recent history

    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

  • Desktop executionGitHub · Repository

    codevisor

    851-labs/codevisor

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Codevisor presents a native application for working with agent-assisted software engineering. 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 licensing 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

    fiber

    aakshintala/fiber

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Fiber provides a multi-provider coding-agent harness focused on runtime and memory efficiency. 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

  • Task orchestrationGitHub · Repository

    AAMARVA

    AAMARVA/AAMARVA

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    AAMARVA connects agent discovery and communication across frameworks, with encryption and credential-protection components. 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 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

    KIN

    abhayzangir1/KIN

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    KIN coordinates local specialist agents with persisted checkpoints and desktop interfaces. 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

    POK-Agent

    Acekorneya/POK-Agent

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    POK Agent combines planning and execution models for Windows computer use, with task memory and local interfaces. Potential use: Connect operator tasking to tools while preserving permission 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

    Connect operator tasking to tools while preserving permission boundaries.

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

    About AI summaries

  • Tool integrationGitHub · Repository

    fastapi-ai-sdk

    Afrazz7/fastapi-ai-sdk

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    FastAPI AI SDK connects FastAPI responses with the Vercel AI SDK for typed streaming 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 using 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

    Insufficient recent history

    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

  • Evaluation & controlsGitHub · Repository

    AgentEval

    AgentEvalHQ/AgentEval

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    AgentEval supplies .NET evaluation tools for agent tool use, retrieval quality and model comparisons. 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

  • Network toolingGitHub · Repository

    hellogrok

    Ahmedabdel6784/hellogrok

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    HelloGrok provides a local proxy for translating model API requests and configuring provider connections. Potential use: Inspect connectivity and access controls before exposing network tools to agents. 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

    Inspect connectivity and access controls before exposing network tools to agents.

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

    About AI summaries

  • Runtime patternsGitHub · Repository

    BaseSIM_APEIRON

    AI-ModCon/BaseSIM_APEIRON

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    BaseSim Apeiron contains agent-harness code for experimenting with self-improving model workflows. 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

    transect

    AI-Safety-Institute/transect

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Transect analyzes transcripts from extended agent evaluations. 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 platform compatibility and operating costs 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

  • Context & retrievalGitHub · Repository

    production-rag-assistant

    aieng-abdullah/production-rag-assistant

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Production RAG Assistant focuses on cited answers over legal and academic material. 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 integrating it, 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

  • Applied workflowsGitHub · Repository

    cs-aim-forge

    ajwadpxgamer-dotcom/cs-aim-forge

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    CS Aim Forge presents a browser-based aiming practice application rather than agent orchestration infrastructure. 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

  • Context & retrievalGitHub · Repository

    atlas-grag

    albertoJr2018/atlas-grag

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Atlas GRAG combines knowledge graphs and vector retrieval for supply-chain risk investigation. 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 integrating it, 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

  • Task orchestrationGitHub · Repository

    alook

    alookai/alook

    Insufficient recent history

    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

  • Reference & discoveryGitHub · Repository

    awesome-opensource-ai

    alvinreal/awesome-opensource-ai

    Insufficient recent history

    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

  • Reference & discoveryGitHub · Repository

    awesome-system-one

    andyrewlee/awesome-system-one

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Awesome System One collects model, agent, implementation, SDK and benchmark resources for further investigation. 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

    ai-models

    anolilab/ai-models

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    AI Models catalogs model providers and comparison information to support model selection. 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

  • Runtime patternsGitHub · Repository

    arcbox

    arcboxlabs/arcbox

    Insufficient recent history

    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

  • Perception toolingGitHub · Repository

    pytorch-pointcloud

    arthurdjn/pytorch-pointcloud

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    PyTorch PointCloud supplies three-dimensional point-cloud models, training scripts and pretrained weights. 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

  • Runtime patternsGitHub · Repository

    Nimbus

    AshishKumar4/Nimbus

    Insufficient recent history

    50-WORD AI EDITORIAL SUMMARY

    Nimbus provides POSIX-style sandbox infrastructure for agents running on Cloudflare. 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 platform compatibility 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