Discover it.
Understand its value.

MrPeppersDev/agent-infrastructure-landscape

MrPeppersDev/agent-infrastructure-landscape

Public summary pending source review. Open the source to investigate this discovery.

xerj-org/xerj

xerj-org/xerj

Public summary pending source review. Open the source to investigate this discovery.

The-AI-Alliance/semiont

The-AI-Alliance/semiont

Public summary pending source review. Open the source to investigate this discovery.

Prithpal-Sooriya/Cloud-Agent-Memory

Prithpal-Sooriya/Cloud-Agent-Memory

Public summary pending source review. Open the source to investigate this discovery.

jb9k62/good2go

jb9k62/good2go

Public summary pending source review. Open the source to investigate this discovery.

zhangfengcdt/memoir

zhangfengcdt/memoir

Public summary pending source review. Open the source to investigate this discovery.

ruvnet/RuVector

ruvnet/RuVector

Public summary pending source review. Open the source to investigate this discovery.

passioncode-ai/project-observatory-dashboard

passioncode-ai/project-observatory-dashboard

Public summary pending source review. Open the source to investigate this discovery.

Charlesfrederickmenningerdateplum166/agent-memory-daemon

Charlesfrederickmenningerdateplum166/agent-memory-daemon

Public summary pending source review. Open the source to investigate this discovery.

Knuckles-Team/epistemic-graph

Knuckles-Team/epistemic-graph

Public summary pending source review. Open the source to investigate this discovery.

Kavi

mohamedhabila/Kavi

AI EDITORIAL SUMMARY

Kavi runs an assistant inside an iOS or Android app. Its documented features include answering questions, researching topics, managing reminders and calendar events, working with selected photos, sharing content and remembering preferences across conversations. It supports configured connections to GitHub, browsers and remote tools. Its tool contracts, state handling and outcome evaluations offer agentic development references. User guide

Chat On Steroids

totec448-spec/chat-on-steroids

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.

GitHub Agentic Workflows

github/gh-aw

50-WORD AI EDITORIAL SUMMARY

GitHub Agentic Workflows turns Markdown instructions into AI workflows executed through GitHub Actions. It can support issue triage, review and repository reporting. For agentic development, its value is structured task briefs with scoped tools and controlled writes. It complements deterministic CI; local desktop SOP execution would need a separate adapter.

milk

scoutme/milk

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.

Invoker

Neko-Catpital-Labs/Invoker

50-WORD AI EDITORIAL SUMMARY

Invoker coordinates persistent task graphs, isolated Git worktrees and merge gates across coding 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 integrating it, check permissions against your requirements in a small controlled test.

agentrove

Mng-dev-ai/agentrove

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.

Q-Core

0design/Q-Core

50-WORD AI EDITORIAL SUMMARY

Q-Core provides a local workflow engine with versioned processes, deterministic checks and human approval gates. 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.

openwop

openwop/openwop

50-WORD AI EDITORIAL SUMMARY

OpenWOP defines a multi-agent workflow protocol with progress monitoring, approval pauses and replay 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 integrating it, check permissions against your requirements in a small controlled test.

ai-workflows

dryvist/ai-workflows

50-WORD AI EDITORIAL SUMMARY

AI Workflows collects reusable GitHub Copilot workflows for repository triage, maintenance and coordinated updates. Potential use: Coordinate task handoffs with explicit responsibilities and review points. 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.

openharness

autonomous-ai/openharness

50-WORD AI EDITORIAL SUMMARY

OpenHarness presents a command center for coding agents working across multiple machines and engineering 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 adoption, check permissions against your requirements in a small controlled test.

protoAgent

protoLabsAI/protoAgent

50-WORD AI EDITORIAL SUMMARY

ProtoAgent provides a local desktop agent workspace with coding-agent connections, plugins and agent communication. 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.

Nimbus

AshishKumar4/Nimbus

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.

tinytools

tinyhumansai/tinytools

50-WORD AI EDITORIAL SUMMARY

TinyTools supplies tool schemas and agent-oriented defaults for connecting applications to AI tools. 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 integrating it, check permissions against your requirements in a small controlled test.

fast-agent

evalstate/fast-agent

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.

yai-agent-core

Gi-Tuu/yai-agent-core

50-WORD AI EDITORIAL SUMMARY

YAI Agent Core supplies an embeddable agent kernel intended for integration into host 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 using a small controlled test.

dsh-suite

whyihaveyou/dsh-suite

50-WORD AI EDITORIAL SUMMARY

DSH Suite catalogs DeepSeek Harness plugins and supplies store, scaffolding and compatibility-checking components. 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.

agentos

framerslab/agentos

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.

ai-assistant-instructions

dryvist/ai-assistant-instructions

50-WORD AI EDITORIAL SUMMARY

AI Assistant Instructions provides reusable development instructions and commands intended to work across coding assistants. 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 adoption, check permissions against your requirements in a small controlled test.

agent-framework-radar

linny006/agent-framework-radar

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.

pi-mcp-adapter

nicobailon/pi-mcp-adapter

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.

alook

alookai/alook

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.

armadra-agent

Owlbay/armadra-agent

50-WORD AI EDITORIAL SUMMARY

Armadra Agent is a standalone coding coordinator designed for embedding within the wider Armadra system. 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.

trending-claude-skills

linny006/trending-claude-skills

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.

claude-code-plugin-tracker

linny006/claude-code-plugin-tracker

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.

codevisor

851-labs/codevisor

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.

scubiee

Usmansayed/scubiee

50-WORD AI EDITORIAL SUMMARY

Scubiee builds local code context through semantic search, relationship mapping, live synchronization and MCP integration. 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.

detent

digitaldrywood/detent

50-WORD AI EDITORIAL SUMMARY

Detent coordinates agent work using GitHub boards, isolated worktrees, validation gates and a serialized merge process. 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 using a small controlled test.

atto

sebastianrcnt/atto

50-WORD AI EDITORIAL SUMMARY

Atto offers a Go terminal harness with shell tools, sessions, context compaction and hooks. 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.

software-factory

theninjadojo/software-factory

50-WORD AI EDITORIAL SUMMARY

Software Factory turns labeled GitHub issues into sandboxed analysis, implementation and pull-request 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 permissions against your requirements in a small controlled test.

SkillEvaluator

NVIDIA/SkillEvaluator

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.

fred-agent-evaluator

fred-agent/fred-agent-evaluator

50-WORD AI EDITORIAL SUMMARY

Fred Agent Evaluator supplies components for evaluating agent behavior during online operation. 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 integrating it, check permissions against your requirements in a small controlled test.

promptic-python-sdk

prompticeu/promptic-python-sdk

50-WORD AI EDITORIAL SUMMARY

Promptic Python SDK provides tracing, prompt optimization and evaluation interfaces through Python and command-line tooling. 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.

triage-kit

ivanbao9783/triage-kit

50-WORD AI EDITORIAL SUMMARY

Triage Kit supports investigating failed agent cases and checking task quality in Harbor 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 permissions using a small controlled test.

agent-evaluation-framework

Lin-chpin/agent-evaluation-framework

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.

FORGE

yassineaqejjaj/FORGE

50-WORD AI EDITORIAL SUMMARY

Forge combines agent evaluation, benchmarking and improvement workflows in a development framework. 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 integrating it, check permissions against your requirements in a small controlled test.

agent-CE

undomestic-georgebeadle691/agent-CE

50-WORD AI EDITORIAL SUMMARY

Agent CE packages web-agent evaluation frameworks for container-based execution and 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 integrating it, check permissions against your requirements in a small controlled test.

loom

ca-mrc/loom

50-WORD AI EDITORIAL SUMMARY

Loom supplies a platform for evaluation and dataset generation in AI development 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 adoption, check permissions against your requirements in a small controlled test.

multimodal-agent-evaluation-handbook

Xiesy0229/multimodal-agent-evaluation-handbook

50-WORD AI EDITORIAL SUMMARY

Multimodal Agent Evaluation Handbook explains evaluation concepts, execution traces and small evaluation systems for beginners. 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 adoption, check permissions against your requirements in a small controlled test.

limen

overment/limen

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.

mecatl

stacklok/mecatl

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.