The AI agents real teams
are picking this week.
Ranked by a weighted score of stack additions, click-throughs, and head-to-head comparisons. No views inflation, no editorial picks — just what users actually do.
| # | Agent | Stack adds | Price |
|---|---|---|---|
| #1 | In Memoria Persistent Intelligence Infrastructure for AI Agents | 0 | Free |
| #2 | Flowllm FlowLLM: Build LLM applications with ease. | 0 | Free |
| #3 | Purrcat PurrCat Agent | 0 | Free |
| #4 | Agent Trail Local dashboard for Claude Code, Codex, OpenCode, OpenClaw and Qoder session history, token usage, cost tracking, tool calls and subagent replay. | 0 | Free |
| #5 | Nautilus Compass Reliability layer for multi-agent setups — keep agents coordinating without an orchestrator. Cross-dialog contracts + drift detection + black-box memory (no LLM extraction). | 0 | Free |
| #6 | FlightBox Record, replay, and diff every LLM call your AI agent makes | 0 | Free |
| #7 | PunamIDE AI-powered native desktop code editor — Tauri 2, React 19, Monaco Editor. Multi-provider AI, agentic tool-calling, technical debt analysis, and full IDE features. | 0 | Free |
| #8 | Gaas GaaS: Gerunds as a Service — an API for AI spinner verbs. Percolating… Reticulating… Prognosticombobulating… | 0 | Free |
| #9 | Codex Agent Mem Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflows. SQLite + FTS5 compact context packs, token savings, read | 0 | Free |
| #10 | VividnessMem Ai Roommates VividnessMem is built on the idea that memory is not storage but changing salience over time. Vividness provides the core forgetting/reinforcement dynamic; associations enable lateral recall; higher l | 0 | Free |
| #11 | Dsl Spa Middleware for simplifying the design, development, and deployment of agents | 0 | Free |
| #12 | Rusty Gitclaw A universal git-native AI agent framework — written in Rust. Single binary. Zero dependencies. 383 models. Blazing fast. | 0 | Free |
| #13 | Welink 🔍微信聊天数据分析的本地化AI-agent(Docker/Windows/MacOS) · AI分身 / 大模型分析 / 好友排行 / 词云 / 情感趋势 / 群聊画像 | 0 | Free |
| #14 | Education Agent Skills 131 evidence-based education skills for Claude, Codex, and any Agent Skills-compatible tool. | 0 | Free |
| #15 | Token Tracker Track token usage across local AI agents (Claude Code, Codex) — CLI dashboard with cost analysis, rate limit monitoring, and session tracking | 0 | Free |
| #16 | Persona Create agentic front-end experiences for the web in VanillaJS™️. Lightweight, extensible, and WebMCP-native. | 0 | Free |
| #17 | Riskguard 开源交易风控层:仓位上限 · 回撤熔断 · 动态仓位(Kelly/波动率) · 防篡改审计 · 实时监控守护。补上量化五层积木唯一缺的一层,核心零依赖。 | 0 | Free |
| #18 | Right Agent agents that run on your claude subscription. multi-agent, sandboxed by default. polished telegram UI. | 0 | Free |
| #19 | Spring Ai Alibaba Multi Agent Demo Cloud-Side Beverage Shop Smart Order Assistant - A distributed multi-agent system built using Spring AI Alibaba Agentic API | 0 | Free |
| #20 | Web Ui 🖥️ Run AI Agent in your browser. | 0 | Free |
| #21 | Golab A blazing-fast, native Golang Model Context Protocol (MCP) Server for controlling and scraping Google Colab locally. | 0 | Free |
| #22 | Agent Script A simple, observable code-writing agent builder in TypeScript. | 0 | Free |
| #23 | Openlive Open, self-hosted runtime for real-time voice agents — a Rust recreation of ChatGPT's Advanced Voice Mode (GPT-Live), model-neutral | 0 | Free |
| #24 | Mex Persistent project memory for AI coding agents. Structured scaffold + drift detection CLI. | 0 | Free |
| #25 | Cognivault CogniVault is a modular, CLI-based multi-agent assistant designed to help you reflect, refine, and organize your thoughts | 0 | Free |
Score weights: stack add ×5, click ×2, compare ×2, view ×0.1. Anonymized — no user information is ever exposed.
Don't guess from a leaderboard.
Get matched to your stack.
The Concierge factors in your role, budget, tools, and compliance posture — popular ≠ right for you. Get personalized matches in 30 seconds.