Agent Infrastructure Is Heating Up
Daily open-source AI market intelligence from AI Rank.
Today’s Top 50 points to a shift from model demos toward production-grade agent systems. Decision models, memory layers, orchestration runtimes, and dev...
New repositories: 0. Changed repositories: 3.
Repositories mentioned
- vectorize-io/hindsight - Hindsight: Agent Memory That Learns
- rohitg00/ai-engineering-from-scratch - Learn it. Build it. Ship it for others.
- obra/superpowers - An agentic skills framework & software development methodology that works.
- NandhaKishorM/laya - Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a...
- google/ax - Google's open agentic orchestration runtime
- jaredpalmer/kev - tiny Jev-like family of decision models built on top of Qwen3.5 you can train and run on your own
- rocketride-org/rocketride-server - High-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model providers, 8+...
- Nasiko-Labs/nasiko - Developer Control Plane for your AI Agents
- farion1231/cc-switch - A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
- stablyai/orca - Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote ru...
- hypit-ai/hypit - Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and...
- browser-use/jev-ultrafast - Fastest and cheapest web agent
- deepseek-ai/deepseek-harness - DeepSeek Harness: Everything is a Plugin.
- mattpocock/skills - Skills for Real Engineers. Straight from my .agents directory.
- jev-chat/jev-chat-jarvis - 装在手机上的对话副驾：在微信 / QQ / X / 飞书里读懂对方、给出候选回复、一键填入输入框，发不发由你。非侵入，只读屏幕，不 hook 不改包。
- dream-num/univer - The Office Harness for AI Agents — Spreadsheets, Docs, Slides, Canvas, Relational Tables, and PDF in one runtime.
- DietrichGebert/ponytail - Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
- affaan-m/ECC - The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode,...
- tt-a1i/archify - Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
- cloudflare/security-audit-skill - A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings
- strands-agents/harness-sdk - Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.
- CopilotKit/openmuse - A personal agent with a browser, terminal, files, and work that keeps going built with CopilotKit and AG-UI.
- anthropics/financial-services -
- browser-use/video-use - Edit videos with coding agents
- DeusData/codebase-memory-mcp - High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms...
- superdesigndev/treg - OpenRouter for agent tools. Join community here: https://discord.gg/6mQYYfFMAn
- firecrawl/firecrawl - The web data API to search, scrape, and interact at scale. 🔥
- alibaba/open-code-review - Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level...
- every-app/open-seo - Open source alternative to Semrush and Ahrefs
- mizorewww/laya-mlx - Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
- shengjidaguai-china/goutoujunshi - 一个先接住情绪、再分析关系并给出可执行策略的 Codex 恋爱军师，内置心理、法律、社会、人文、哲学、婚姻家庭与性学知识库，支持多元关系。
- TNT-Likely/PanWatch - 盯盘侠 PanWatch · 自托管 AI 盯盘助手，集成 TradingAgents 多 Agent 投资决策 | A股/港股/美股实时监控、持仓管理、智能分析、全渠道推送
- bojieli/ai-agent-book - 《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
- agent-substrate/substrate - Agent Substrate: the core system
- HKUDS/CLI-Anything - "CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
- debpalash/VoiceStudio - VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook cr...
- dataelement/dsh-desktop - DSHDesktop：DeepSeek Harness Desktop / DeepSeek Harness 桌面版
- Tencent/WeKnora - Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
- Human-Agent-Society/reef - Continual learning infra for self-improving agents
- arcboxlabs/arcbox - Run AI agents on real and isolated machines — own kernel, filesystem, and network — with <100ms boot. Local first, OCI compatible, pure Rust.
- ChenLiu-1996/figures4papers - My Python scripts to make high-quality figures for publications in top AI conferences and journals.
- unreallabsai/unreal-agent - Async-first agent harness
- allenpeng0705/EnvoyMesh - Decentralized P2P mesh for autonomous AI agents — self-sovereign identity, peer-to-peer chat, and on-device AI that negotiates tasks on your behalf. No...
- BuilderIO/agent-native - A framework for building agentic apps
- NousResearch/hermes-agent - The agent that grows with you
- grft-dev/graftcode - Connect any code. Call as dependency. The official repository for Graftcode: the integration-free development layer that lets you call methods across la...
- davila7/claude-code-templates - CLI tool for configuring and monitoring Claude Code
- iAmCorey/Wake - All your AI agent sessions in one place — browse, search, resume. Rust + GPUI.
- Graphify-Labs/graphify - Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, an...
- ayghri/i-have-adhd - A skill to stop your coding agent from burying the answer. ADHD-friendly output.