All tags
Catalogue tag

#ai-agent

Every repository in the public record carrying this tag — from its GitHub topics or the keywords its package registries publish. Health is measured under the same versioned methodology as the rest of the record.

470 records
Tagged “ai-agent”Ranked by health index
npm
50Moderatehealth index
eli-labz/Third-Eye
A production-grade OSINT platform that provides situational awareness across multiple intelligence domains.
TypeScript★ 936Jul 21, 2026
MITJul 21, 2026 · metrics 2.10.0
npm
50Moderatehealth index
mleoca/ucn
Universal Code Navigator
JavaScript★ 1↓ 2,153/moJul 16, 2026
MITJul 16, 2026 · metrics 2.10.0
npm
50Moderatehealth index
pipilot-dev/anyclaude-sdk
Claude Code agent capabilities (tools, tool loop, MCP, sub-agents, sessions) for ANY OpenAI/Anthropic-compatible LLM — in the browser (WebContainer), Node, and Bun. No backend required.
TypeScript · HTML★ 0↓ 10.8K/moJul 24, 2026
MITJul 24, 2026 · metrics 2.10.0
PyPI
50Moderatehealth index
tmwgsicp/wechat-download-api
一款完全开源的微信公众号文章获取、RSS 订阅 API 服务,支持整号文章一键导出 7 种格式(Markdown/HTML/Word/PDF/EPUB/Excel/JSON)、IP 代理池反风控、MCP 接入各种 AI Agent 工具。
Python · HTML★ 943Aug 2, 2026
AGPL-3.0Aug 2, 2026 · metrics 2.10.0
PyPI
48Weakhealth index
aetna000/aetnamem
AetnaMem /ET-nuh-mem/ is agent Memory delivers fully local long-term auditable, proof-ready memory for AI Agents via a 4-tier progressive pipeline, with zero external API dependencies, it supports OpenClaw, install it via pip.
Python · TeX★ 3↓ 2,067/moAug 1, 2026
AGPL-3.0Aug 1, 2026 · metrics 2.10.0
Go
48Weakhealth index
alanchenchen/suna
Local-first terminal agent runtime with isolated subtasks and intent-aware safety.
Go★ 14Jul 28, 2026
Custom licenseJul 28, 2026 · metrics 2.10.0
PyPI
48Weakhealth index
bxw91/brainpalace
Vector Graph RAG for code & docs with Persistent Chat-Session Memory — BM25 (multi-lang), AST chunking. Hybrid, Compute, Scan, Timeline, Absence, Salience. Graph + temporal knowledge. Privacy Stamps. Source Adapters. Chat summarisation + verbatim copy + free scan. Git indexing. CLI, MCP and Claude Code plugin. Ollama or cloud LLMs. Dashboard.
Python★ 2↓ 5,690/moJul 18, 2026
MITJul 18, 2026 · metrics 2.10.0
Go
48Weakhealth index
cavibora/bugbuster-code
Model-agnostic AI coding agent for your terminal - 22 tools, 5 LLM providers, multimodal, 8 languages
Go★ 3Jul 18, 2026
MITJul 18, 2026 · metrics 2.10.0
npm
48Weakhealth index
lightningfaucet/lightning-wallet-mcp
MCP Server for Lightning Faucet - Give your AI agent a Bitcoin wallet
JavaScript · TypeScript★ 9↓ 1,106/moJul 19, 2026
MITJul 19, 2026 · metrics 2.10.0
npm
48Weakhealth index
xuhancn/hermes-to-claude
Local MCP bridge between Hermes Agent and Claude Code — no Pro/Max required
JavaScript★ 1↓ 3,941/moJul 25, 2026
MITJul 25, 2026 · metrics 2.10.0
npm
47Weakhealth index
Callmedas69/cognitive-OS
No repository description published.
TypeScript★ 0↓ 3,448/moJul 27, 2026
MITJul 27, 2026 · metrics 2.10.0
npm
47Weakhealth index
chipallen2/snazi
No messages for you. A communication gating layer for AI agents to prevent prompt injection.
TypeScript · JavaScript★ 3↓ 3,728/moJul 23, 2026
MITJul 23, 2026 · metrics 2.10.0
Go
47Weakhealth index
shotforward/codewithphone
Code with your phone. Run AI coding agents (Claude, Gemini, Codex) on your machine, control from your phone.
Go★ 3Jul 18, 2026
Apache-2.0Jul 18, 2026 · metrics 2.10.0
47Weakhealth index
simonlin1212/a-stock-data
A股全栈数据工具包 · 十一层架构 · 54端点 · 19数据源 · 零鉴权 | Full-stack China A-share data toolkit for AI agents — 11 layers, 54 endpoints, 19 sources, zero-auth
Mixed★ 9,283Aug 28, 2026
Apache-2.0Aug 28, 2026 · metrics 2.10.0
npm · PyPI
47Weakhealth index
thienan230427/TaxSentry
No repository description published.
Python★ 0↓ 4,468/moJul 20, 2026
MITJul 20, 2026 · metrics 2.10.0
npm
45Weakhealth index
ArisRoman/cyberaudit-skill
Universal security audit skill for AI agents. 52 pure Markdown files encoding 15 years of pentest expertise — web & mobile security, OWASP-aligned, CVSS scoring, compliance checks, zero dependencies.
TypeScript · JavaScript★ 0↓ 2,331/moJul 25, 2026
No licenseJul 25, 2026 · metrics 2.10.0
npm
45Weakhealth index
NHTIO/ADK
A read-only, sanitized GitHub mirror of the open source release for @nhtio/adk
TypeScript★ 2↓ 5,509/moJul 25, 2026
MITJul 25, 2026 · metrics 2.10.0
Go
45Weakhealth index
brianly1003/cdev
Go daemon for monitoring and controlling Claude Code & Codex sessions via JSON-RPC, WebSocket streaming, multi-workspace orchestration, and QR pairing.
Go★ 0Aug 23, 2026
MITAug 23, 2026 · metrics 2.10.0
npm
45Weakhealth index
dannyphantomx64/aether-code
Uncensored AI coding agent for your terminal — Claude Code alternative with MCP support. Drives IDA Pro, Roblox Studio, Wireshark, Blender, and any MCP server.
JavaScript★ 3↓ 11.4K/moJul 19, 2026
MITJul 19, 2026 · metrics 2.10.0
PyPI
45Weakhealth index
imperalcloud/webbee-code
Webbee Code 🐝 — the imperal.io Cloud coding ultra-agent in your terminal
Python★ 0Jul 17, 2026
MITJul 17, 2026 · metrics 2.10.0
PyPI · npm
45Weakhealth index
motojinc25/chatwalaau
The localhost AI Agent Runtime - Chat UI, Tools, RAG, and MCP in one pip install
Python · TypeScript★ 2↓ 5,382/moJul 31, 2026
Apache-2.0Jul 31, 2026 · metrics 2.10.0
npm
45Weakhealth index
rogersialves/wendkeep
Persistent-memory harness for AI coding agents — captures Claude Code/Codex sessions into an Obsidian vault, plus a native spec->change->verify loop. Local-first, zero runtime deps.
JavaScript★ 0↓ 8,811/moJul 15, 2026
MITJul 15, 2026 · metrics 2.10.0
npm · PyPI
44Weakhealth index
CHNAICORP/cortx
Cortx — AI Agent runtime | Harness Agent + Agentic Loop | 43 tools | Python + TypeScript
Python · TypeScript★ 0↓ 8,726/moJul 21, 2026
MITJul 21, 2026 · metrics 2.10.0
npm
44Weakhealth index
MelnixDev/context-goblin
An OpenCode plugin that hoards tiny project-context notes so agents read less and waste fewer tokens.
TypeScript · Shell★ 1↓ 3,137/moJul 16, 2026
MITJul 16, 2026 · metrics 2.10.0
npm
44Weakhealth index
OpenOBA/erdl-mcp-server
Stop reminding your Agent to behave. Teach it. One when/then sentence is all it takes.
TypeScript★ 2↓ 234/moSep 5, 2026
Custom licenseSep 5, 2026 · metrics 2.10.0
npm
44Weakhealth index
ThalesGnimavo/casp
CASP — the Coding-Agent State Protocol. A 200-line discipline for AI-coding sessions.** Machine-verifiable session state + drift validator + canonical templates. Works with Claude Code, Cursor, or anything that drives a repo with a session loop. Built by Thales (Juste Gnimavo) (https://thalesandhisaictoclaude.com)
TypeScript · JavaScript★ 0↓ 2,212/moJul 30, 2026
MITJul 30, 2026 · metrics 2.10.0
npm
44Weakhealth index
absolutejs/isolated-jsc
No repository description published.
TypeScript★ 0↓ 2,495/moAug 5, 2026
Custom licenseAug 5, 2026 · metrics 2.10.0
npm
44Weakhealth index
degausai/wonda
Wonda CLI — AI-powered content creation from your terminal
TypeScript★ 136↓ 727/moJul 19, 2026
No licenseJul 19, 2026 · metrics 2.10.0
PyPI
44Weakhealth index
hypn4/tossinvest-mcp
MCP server for Toss Securities (토스증권) Open API: Korean stock (KRX) quotes, holdings, orders & technical analysis for Claude and other AI agents. Read-only by default.
Python★ 1↓ 205/moJul 18, 2026
Apache-2.0Jul 18, 2026 · metrics 2.10.0
npm
44Weakhealth index
manovagyanik1/clipy-mcp
Clipy is the first agent-readable screen recorder — free, no watermark, for Mac, Chrome, and the web. One share link: humans watch the video, AI agents read the summary, key moments, and transcript.
JavaScript★ 2↓ 2,780/moJul 26, 2026
MITJul 26, 2026 · metrics 2.10.0