AI Dev Impact Lab JA
← Topics ranking · 2026-05
GITHUB TOPIC

#agents

GitHub repositories that have self-applied the topic "agents" — a creator-tagged metadata that surfaces how AI projects describe themselves.

17
tagged repos
19
top 17 stars
9
with tool sigs
17
shown

REPOS Repos for #agents (top 17 by stars)

rudrankriyam/Google-Health-CLI

Unofficial Google-Health-CLI for the Google Health API, written in Go

Go 14 AI 10 1 sig
steph-frtech/claude-code-up

npx claude-code-up — bootstrap a Claude Code project with curated agents, skills, MCPs, scaffolders & lib bundles. JSON-driven decision tree, e2e verified.

Shell 1 AI 100 Solo 1 sig live ↗
usernotfinded/atlas-agent

Trading agent that learns from his mistakes

Python 1 AI 100 1 sig
AISquare-Studio/office

An opinionated 6-agent solo-founder team for Claude Code. Same numbered roster, every project.

Python 1 AI 70 live ↗
metyatech/symphony-metyatech

TypeScript implementation of the OpenAI Symphony service specification: a long-lived CLI service that polls Linear, creates one workspace per issue, and launches a Codex app-server worker.

TypeScript 1 AI 60 Solo 2 sig live ↗
AysajanE/staged-workflow-runner

Manifest-driven runner for staged OpenAI Responses workflows.

Python 1 AI 60 1 sig
DmitryDmitriadi/ai-engineering-portfolio

Hub for AI engineering case studies: multi-agent orchestration, RAG, browser automation, observability + evaluation.

0 AI 100
DmitryDmitriadi/multi-agent-workflow-platform

Case study: live AI consultant — typed conversation graph, source-grounded knowledge, reviewer-gated utterances, in-process cost guardian.

0 AI 100
geo-ai-advisory/claude-code-kit

Готовая система агентов / хуков / Obsidian-vault для Claude Code на macOS. Smart installer сканирует твои проекты и собирает рабочую среду под ключ. 23 агента, 22 хука, 4-tier memory, VoiceInk free build.

Python 0 AI 100 Solo live ↗
Ggrryta/agent-mesh

A gateway + skill letting Claude Code agents collaborate across machines

Go 0 AI 100
Mearman/agent-permissions

Cross-agent permission policy schema, evaluator, codecs, and CLI — one .agents/permissions.json for every coding agent

TypeScript 0 AI 100 2 sig
hiper2d/marlow

Long-loop agent experiment: Werewolf ops + AI safety research stream. Runs on Claude Code.

Python 0 AI 70 1 sig
Fantasymax/easy-build-skills

Let AI research you back—answer ~15 multiple-choice questions to get YOUR AI config (CLAUDE.md / AGENTS.md / custom skills), instead of copy-pasting templates. By FantasyMax.

0 AI 70
kamalchibrani-ai/FinAdvisor

FinSight — Streamlit + FastAPI app for India-focused equity portfolios and an agentic LangGraph assistant (OpenAI tools, Neon Postgres, optional Redis & Pinecone). Deploy-ready with Render.

Python 0 AI 60 Solo live ↗
felixgeelhaar/nomi

Local-first, state-driven AI agent platform. Plan-review before execution, capability-gated tools, BYO LLM (Ollama / Anthropic / OpenAI). Tauri desktop + Go runtime.

Go 0 AI 50 Solo 1 sig live ↗
denn-gubsky/loomcycle

Lightweight multi-tenant agentic runtime in one Go sidecar. Owns the LLM tool-use loop across Anthropic, OpenAI, and Ollama with native prompt-cache control, MCP tool dispatch, and per-tenant fairness. TypeScript and Python adapters over HTTP+SSE. Powers JobEmber.

Go 0 AI 50 Solo 1 sig live ↗
CREVIOS/agentic-search

Fastest agentic search substrate. S3-native ls/glob/read/grep with tree-sitter spans, parallel fan-out, MCP server. Rust.

Rust 0 AI 45

RELATED Other topics · full topics ranking →

#claude-code

122

#ai-agents

73

#claude

73

#mcp

71

#llm

67

#python

56

#developer-tools

49

#ai

45

#anthropic

42

Aggregated by case-insensitive match against topics_json of each repo's latest content snapshot. methodology