Awesome-AITools
Collection of AI-related utilities. Welcome to submit pull requests /收藏AI相关的实用工具，欢迎提交pull requests
by ikaijua · updated 4h ago · imported from GitHub
Installs0+0/7d
Security score82/100
Retention 14d0%
GitHub stars6.2K
Skill logic
Execution graph
README
<div align="center">
<h1>Awesome AI Tools</h1>
<a href="https://awesome.re"><img src="https://awesome.re/badge.svg"/></a>
<br>
<a href="https://github.com/ikaijua/Awesome-AITools/stargazers"><img src="https://img.shields.io/github/stars/ikaijua/Awesome-AITools?style=social" alt="Stars"></a>
<a href="https://github.com/ikaijua/Awesome-AITools/network/members"><img src="https://img.shields.io/github/forks/ikaijua/Awesome-AITools?style=social" alt="Forks"></a>
<a href="https://github.com/ikaijua/Awesome-AITools/commits"><img src="https://img.shields.io/github/last-commit/ikaijua/Awesome-AITools" alt="Last Commit"></a>
</div>
English | 中文
This repo collects awesome AI tools. Welcome everyone to recommend more awesome AI tools together! Please use the following template as a reference for your recommendations. issue
<a href="https://www.buymeacoffee.com/ikaijuaawesomeaitools" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/default-orange.png" alt="Buy Me A Coffee" height="41" width="174"></a>
💎 Sponsor
<p align="center"> A huge thank you to our sponsors for their generous support! </p> <details open> <summary>Click to collapse</summary> <table align="center" cellpadding="10" style="width:100%; border-collapse:collapse;"> <tr align="center"> <td width="500" valign="middle" align="center"> <sub> <a href="https://www.xuanshuapi.com/" target="_blank"> <img alt="Xuanshu API" src="assets/sponsors/xuanshuapi-en.jpg" /> </a> <br> 【<b>Xuanshu API</b> is a next-generation AI model routing gateway for enterprises, technical teams, and individual developers. It provides one-stop API access to world-class top models (Claude, GPT, Grok, etc.) with enterprise-grade stability. Recharge and enjoy 20% off, models starting from 20% of the original price, $5 free upon registration, invoice support for enterprises. Click <a href="https://www.xuanshuapi.com/register?aff=AWESOME-AI-TOOLS&promo=AWESOME-AI-TOOLS" target="_blank">this link</a> to register and get an extra $5 credit.】 <br> <a href="https://www.xuanshuapi.com/" target="_blank"> <img src="https://img.shields.io/badge/Visit%20Site-blue?style=flat-square" alt="Visit Xuanshu API website"> </a> </sub> </td> </tr> </table> </details>All Categories
- All Categories
- AI Assistants & Proprietary Models
- Open Source LLMs
- LLM Leaderboard
- AI Agent
- Agent Skills
- AI News & Information
- AI Coding
- General LLM Applications
- Office Collaboration CLI/MCP
- AI Finance & Quant Investment
- AI Image Creation and UI Design
- Video Creation
- AI Infrastructure Platform
- GPU Programming
- LLM Prompts
- LLM training platform
- LLM Inference & Deployment
- Writing
- Translation
- Speech Recognition
- Text To Speech
- Music Recognition
- Voice Processing
- AI generated music or sound effects
- Speech translation
- Video Content Summary
- Academic research
- OCR
- AI Detection
- Humanoid Robots
- Embodied AI & Simulation
AI Assistants & Proprietary Models
| Name | Description | Links | Fees |
|---|---|---|---|
| ChatGPT | 🌟 OpenAI's AI assistant. Current flagship: GPT-6 Astra; September's GPT-6 Sol and GPT-6 Luna cut API prices ~50% ($2/$10 and from $0.10 input per M tokens) and are free within consumer limits. Differentiation: persistent memory and user profile — remembers context across conversations and feels the most personalized; best general-purpose assistant for coding, writing, and daily tasks. Intro | 1. URL<br>2. API | Free/Paid |
| Gemini | 🌟 Google's AI assistant. Current flagship: Gemini 3.8 Flash (with a cybersecurity-focused 3.8 Flash Cyber variant). Differentiation: native multimodality and Deep Research — best for image understanding/generation and web-based research; tightly integrated with Google Drive and Workspace. Intro | 1. URL<br>2. API | Free/Paid |
| Claude | 🌟 Anthropic's AI assistant. Current flagship: Claude Fable 5.1 (general) / Claude Mythos 5.1 (trusted-access); September's Claude Opus 5.5 (first of the 5.5 family) matches Fable 5.1 on most tasks at ~40% lower cost ($4/$20 per M tokens, 30%+ faster output). Differentiation: Cowork mode turns the chatbot into an agent that can pull financial data, build Excel forecasting models, and execute workflows; strongest at coding, long-context reasoning, safety, and enterprise use. Fable 5.1 lowers typical cost by ~25% and cybersecurity false positives by ~60%. Intro | 1. URL<br>2. API | Free/Paid |
| DeepSeek | DeepSeek's AI assistant. Current flagship: DeepSeek-V4.1-Flash (released Sept 10, 2026; new Causal-Encoder-Decoder architecture, 552B MoE with asymmetric activation, native multimodality — official benchmarks show it surpassing V4-Pro at lower cost, and V4-Pro is being retired with requests migrated to Flash). Differentiation: reasoning-to-cost ratio — top open-source coding/agentic capability at very low API price. | 1. URL<br>2. API | Free/Paid |
| Kimi Chat | Moonshot AI's AI assistant. Current flagship: Kimi K3. Differentiation: 2.8T-parameter MoE + 1M-token context — optimized for software engineering, repository-scale analysis, and long-document reasoning. | 1. Kimi<br>2. Moonshot AI | Free |
| GLM | Zhipu AI's AI assistant. Current flagship: GLM-5.3 (743B MoE, 40B active, released Aug 14, 2026); also offers GLM-5.3-Flash (320B/18B MoE, native multimodal, MIT open weights, 1M context) with coding/agent performance near Claude Opus 4.8 at much lower cost. Differentiation: agentic coding, repo-scale analysis, cyber-defense, and long-context reasoning. | 1. URL<br>2. API | Free/Paid |
| Grok | SpaceXAI's AI assistant (formerly xAI). Current flagship: Grok 4.7 (released Sept 21, 2026; ~2.1T parameters, focused on coding and knowledge work, 500K context, text+image input, four reasoning-effort tiers; API $2/$6 per M input/output tokens). Differentiation: real-time X data access — its moat is live internet/X posts as an information source; best for real-time news and events. Intro | 1. URL<br>2. API | Free/Paid |
| Qwen | Alibaba's AI assistant. Current flagship: Qwen3.8-Max (GA Aug 3, 2026; open weights for Qwen3.8-27B released Aug 14). Differentiation: open-weight 2.4T MoE + long-horizon agentic reasoning — strong coding/deep research with 1M context and native multimodality. | 1. URL<br>2. API | Free |
| Dola | ByteDance's AI assistant. Current flagship: Doubao-Seed-2.1 Pro. Differentiation: clean, intuitive UI with strong general capabilities — straightforward chat experience for everyday tasks. | 1. URL<br>2. API | Free |
| Meta Muse | 🌱 Meta's personal AI agent that does tasks instead of chatting: books travel, fills forms, shops, and manages email/calendars, paying via one-time Stripe Link cards. Runs in an isolated VM with a host-side Sentinel approving every sensitive action; powered by Meta's proprietary Muse Spark 1.3 model. Reached #1 on the US App Store free chart ~10 days after launch (Sept 8, 2026), overtaking ChatGPT. Currently US-only (18+); free tier ~100M tokens/week, paid plans from $20/mo. Intro | URL | Free/Paid |
| Jev | 🌱 TypeSafe AI's "System One" decision model (early access) — it never generates text, returning typed answers from three primitives (Choice/Score/Noul) with calibrated probabilities via RLCD training, so confidence matches accuracy. Officially 20-200x faster and 1/40-1/400 cheaper than frontier LLMs on structured tasks; input $0.042/M tokens, output free; 70-500ms latency. Founded by ex-OpenAI researcher Diogo Almeida (co-inventor of RLHF); $40M seed led by DCVC. Note: official figures, not yet independently verified. Intro | URL | Free/Paid |
Open Source LLMs
| Name | Description | Links | Fees |
|---|---|---|---|
| Kimi K3 | 🌟 Moonshot AI's 2.8T-parameter flagship open-weight model. Native visual understanding, 1M-token context window, and Kimi Delta Attention (KDA). The first open-source model in the 3-trillion-parameter class; full weights were released on July 27, 2026 on Hugging Face under a Modified MIT license. Intro | Technical Blog Hugging Face | Free |
| DeepSeek-V4 | 🌟 DeepSeek's 4th generation flagship model, MIT-licensed and open-weight on Hugging Face. V4-Pro 0813 GA rolled out Aug 13, 2026; V4-Pro (1.6T MoE, 49B activated) and V4-Flash (284B MoE, 13B activated) share a 1M-token context and native multimodality, and V4-Flash-Vision-Exp was added Aug 21. V4.1-Flash followed on Sept 10, 2026 — the first model on a new Causal-Encoder-Decoder architecture: a 552B MoE with asymmetric activation (8B input / 16B output), native multimodal vision, and MIT open weights; official benchmarks show it surpassing V4-Pro at lower price, and V4-Pro is scheduled to go offline on Sept 14, 2026 with requests migrated to V4.1-Flash. Architecture upgrades: Hybrid Attention (CSA + HCA) cuts long-context inference FLOPs to ~27% of V3.2 and KV cache to ~10%; Manifold-Constrained Hyper-Connections (mHC) stabilizes residuals; Muon optimizer for faster convergence. Pre-trained on 32T+ tokens. Each model ships with three reasoning effort modes — Non-think (fast), Think High, and Think Max — where Pro-Max is the strongest coding/agentic mode of the V4 generation. Intro | Hugging Face | Free |
| DeepSeek-R1 | DeepSeek's first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step, demonstrated remarkable performance on reasoning. | Github  | Free |
| DeepSeek-V3 | A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. | Github  | Free |
| Qwen3 / Qwen3.8 | Alibaba Cloud's open-weight LLM/VLM families. Qwen3-2507 offers Instruct and Thinking variants (235B-A22B, 30B-A3B, 4B) with 256K–1M context. Qwen3.8 adds the 27B dense vision-language model (released Aug 14, 2026) with image/video input, 262K context, and strong agentic coding benchmarks; Qwen3.8-Flash-Next (125B total / 6B active, Aug 26) previews the Qwen4 architecture with GDN+QSA hybrid attention and 262K native context extendable to 1M. | Github  Hugging Face | Free |
| GLM-5.3-Flash | Zhipu's open-weight (MIT) natively multimodal MoE model (320B total / 18B active), released Aug 26, 2026. A hybrid sparse + linear attention architecture cuts attention compute by ~3× and KV cache by ~4.4×, with 1M context; matches Claude Opus 4.8 on Zhipu's composite intelligence index at roughly 1/40 the API price. | Hugging Face | Free |
| Gemma 4 | Google's latest open source large language model series, released Apr 2, 2026 and built on the Gemini architecture. Comes in four sizes: Effective 2B, Effective 4B, 26B MoE, and 31B Dense; offers improved performance, longer context windows (up to 256K), native vision/audio, and better multilingual support. | Github  | Free |
| Muse Glimmer | Meta's 30B-parameter open-weight multimodal model for local agents, released Aug 10, 2026 under Apache 2.0. Features ~131K context, text/image input, tool use, 4-bit quantized variants for 24–32 GB VRAM, and DFlash speculative decoding. Distilled from Muse Spark (now at version 1.3). Intro | Hugging Face | Free |
| Llama 4 | Meta's latest open-weight multimodal model family. Features mixture-of-experts architecture with variants such as Scout (10M-token context) and Maverick (400B total/17B active params), supporting text and image input. | GitHub  | Free |
| Mixtral | Mixtral 8x7B, a high-quality sparse mixture of experts model (SMoE) with open weights. Mixtral outperforms Llama 2 70B on most benchmarks with 6x faster inference. It matches or outperforms GPT3.5 on most standard benchmarks. <br>paper：https://arxiv.org/pdf/2401.04088.pdf <br>news：https://mistral.ai/news/mixtral-of-experts/ | mistral-inference  <br>mistral-finetune  | Free |
| grok-1 | A large language model open sourced by xAI | Github  | Free |
| Phi-4 | Microsoft's open-weight small language model (SLM) family. Includes general, reasoning, multimodal, and vision variants (e.g., Phi-4-mini, Phi-4, Phi-4-multimodal, Phi-4-reasoning-vision) designed for efficient on-device and cloud deployment. | Github  | Free |
LLM Leaderboard
| Name | Description | Links | Fees |
|---|---|---|---|
| LMSYS Chatbot Arena Leaderboard | 🌟 LMSYS Chatbot Arena is a crowdsourced open platform for LLM evals. Collected over 1,000,000 human pairwise comparisons to rank LLMs with the Bradley-Terry model and display the model ratings in Elo-scale. | URL | Free |
| Artificial Analysis | Artificial Analysis is a platform that provides AI model and service provider comparisons and benchmarks to help users make informed decisions when choosing AI models and service providers. The platform provides comparative data on a wide range of popular AI models, including OpenAI's GPT-4, Meta's Llama 4, and Anthropic's Claude series, covering performance metrics such as response time, latency, and cost. | URL | Free |
| LiveCodeBench | LiveCodeBench is a holistic and contamination-free evaluation benchmark of LLMs for code that continuously collects new problems over time. Particularly, LiveCodeBench also focuses on broader code-related capabilities, such as self-repair, code execution, and test output prediction, beyond mere code generation. | URL | Free |
| StructEval | StructEval is a TMLR 2025 benchmark and public leaderboard for evaluating LLM structured-output generation and conversion across 2,035 examples, 18 text and renderable formats, and format-specific structural and visual checks. | Leaderboard Paper Github | Free |
| LLM Stats | LLM Stats, the most comprehensive LLM leaderboard, benchmarks and compares API models using daily‑updated, open‑source community data on capability, price, speed, and context length. | URL | Free |
| ModelCap | ModelCap publishes live AI model rankings (the ModelCap Index) compiled only from named public sources — benchmark boards such as SWE-bench, ARC-AGI and BFCL, Arena ratings and provider prices — with an evidence tier and score interval per model, per-benchmark leaderboards, head-to-head model comparisons, provider pricing pages and a CC BY 4.0 JSON/CSV dataset. | URL | Free |
| Price Per Token | Compare LLM API pricing across 200+ models from OpenAI, Anthropic, Google, and more. Includes token counters, cost calculators, and benchmark comparisons. | URL | Free |
| BenchGecko | The data layer of the AI economy. AI model benchmark leaderboard with cross-provider pricing comparison across hundreds of providers. Tracks thousands of models across 128 benchmarks, AI economy indicators, agent leaderboard, and MCP server directory. Free API. | URL | Free |
AI Agent
| Name | Description | Links | Fees |
|---|---|---|---|
| Claude Code | 🌟 Anthropic's AI coding agent. Available in the terminal CLI, VS Code/Cursor/JetBrains IDE plugins, desktop app, and web. Built on the Claude model family, it offers long-context codebase understanding, multi-file editing, shell command execution, MCP extensions, skills/hooks/subagents, CLAUDE.md project rules, and automatic memory. Supports Remote Control to continue local sessions from your phone or browser. Intro Comparison | Github<br>  | Free |
| Codex | 🌟 OpenAI's open-source (Apache-2.0) terminal coding agent, written in Rust. Supports the terminal CLI, VS Code/Cursor/Windsurf IDE extensions, Codex App/desktop app, and Codex Web cloud tasks. It can understand and modify code directly, with kernel-level sandboxing, MCP, skills/plugins/hooks, subagents, and Remote SSH. Active sessions sync across phone/desktop/web via the ChatGPT relay. Intro Comparison | Github  | Free |
| Kimi Code | 🌟 Moonshot AI's AI coding agent CLI that runs in your terminal. Reads and edits code, runs shell commands, searches files, fetches web pages, and plans next steps based on feedback. Supports video input, AI-native MCP configuration, subagents, lifecycle hooks, and ACP editor integration (Zed, JetBrains). Intro Comparison | Github  | Free |
| Manus | 🌱 An action engine that goes beyond answering questions to executing tasks, automating workflows, and extending your service capabilities. Intro | URL | Free Trial/Paid |
| DeepSeek Harness | 🌱 DeepSeek's open-source (MIT) agent harness released on August 13, 2026. A full agent runtime (CLI + Web UI at 127.0.0.1:3080) with an "everything is a plugin" architecture powered by Cordis. Ships 40+ first-party packages (LLM, MCP, LSP, ACP, sandbox, skills, subagents, sessions, tools, plans, scheduling, web, shell, etc.) and bilingual EN/ZH architecture docs. Currently developer preview — breaking changes expected. Intro | Github  | Free |
| Antigravity | Google's agent-first AI coding platform, Antigravity 2.0, delivered as a standalone desktop app, IDE, terminal CLI (agy), and SDK, replacing Gemini CLI. Built around Gemini 3.5–3.8 Flash and supporting Claude, GPT-OSS, and other models via model picker. Features Editor and Manager views for orchestrating multiple autonomous agents, integrated browser/terminal, verifiable Artifacts (plans, screenshots, recordings), subagents, hooks, and scheduled tasks. Intro | URL | Free during preview |
| Pi | Open-source (MIT) self-extensible coding agent by earendil-works. Monorepo architecture with pi-coding-agent (interactive CLI), pi-agent-core (tool calling and state management), pi-ai (unified multi-provider LLM API), pi-tui, and telemetry. Features plugin architecture, supply-chain hardening (pinned deps, shrinkwrap, audit), and sandboxing patterns (Gondolin, Docker, OpenShell). Intro | Github  | Free |
| Grok build | xAI's terminal-based AI coding agent, open-sourced and written in Rust. Runs as a full-screen, mouse-interactive TUI that understands your codebase, edits files, runs shell commands, searches the web, and manages long-running tasks. Supports interactive, headless (scripting/CI), and ACP editor-embedded modes, with MCP servers, skills, plugins, hooks, and sandboxing. Intro | Github  | Free |
| browser-use | Open-source Python library that enables AI agents to control web browsers. Supports natural-language task execution, DOM extraction, form filling, multi-step navigation, and integration with any LLM via a simple API. Useful for building web agents, automated testing, and data extraction workflows. Intro | GitHub  | Free |
| Obscura | Open-source (Apache-2.0) headless browser engine written in Rust for AI agents and web scraping. A drop-in replacement for headless Chrome via the Chrome DevTools Protocol, compatible with Puppeteer/Playwright: ~30 MB memory, instant startup, and a built-in stealth mode with anti-fingerprinting and tracker blocking. | GitHub  | Free |
| Cua | Open-source infrastructure for Computer-Use Agents (CUA). Provides sandboxes, drivers, and SDKs for macOS, Windows, Linux, and Android, enabling AI to control full desktops just like a human. Intro | GitHub  | Free |
| OpenClaw | Open-source self-hosted AI agent that runs locally and autonomously executes tasks. Connects to WhatsApp, Telegram, Slack, Discord and other messaging platforms, with browser control, system access, and persistent memory. Developed by Peter Steinberger, one of the fastest-growing open-source projects. Intro | Github  | Free |
| OpenWorker | Open-source, local-first desktop AI coworker by Andrew Ng. Delivers finished work (documents, Slack replies, calendar updates, reports) rather than chat answers. Supports 35+ app connectors, MCP, and bring-your-own-key models (OpenAI, Anthropic, Gemini, DeepSeek, Kimi, Qwen, Ollama, etc.) with local storage of data and credentials. Intro | Github  | Free |
| autoresearch | An autonomous AI agent for machine learning research by Karpathy. It can formulate hypotheses, modify training code, run experiments, and evaluate results autonomously to find performance improvements. | Github  | Free |
| ml-intern | An open-source, autonomous AI agent by Hugging Face designed to function as a specialized Machine Learning Engineer. It handles the end-to-end ML lifecycle, including researching papers, writing code, running experiments, and shipping models to the Hugging Face Hub. Intro | Github  | Free |
| Dexter | Autonomous financial research agent designed to perform deep analysis by thinking, planning, and learning through iteration. Specialized for the financial domain. Intro | Github  | Free |
| Multica | Open-source managed agents platform to integrate AI coding agents (Claude Code, Codex, Cursor, Copilot, OpenCode, OpenClaw, Hermes, Gemini, Pi, Kimi, Kiro CLI, and more) into dev teams as first-class teammates. Features task assignment, progress tracking, reusable skills, and local daemon auto-detection of installed agent CLIs. Intro | Github  | Free/Paid |
| Paperclip | Open-source AI agent orchestration platform that models AI operations as a company. Define org charts, reporting lines, budgets, and governance policies, then let agents work autonomously within that structure. Supports OpenClaw, Claude Code, Codex, and other agent backends. Heartbeat-based execution with cost controls and audit trails. Intro | Github  | Free |
| Symphony | OpenAI's open-source project-to-delivery harness. Turns project requirements into isolated, autonomous implementation runs; agents monitor boards like Linear, open PRs, and merge code with proof-of-work (CI status, review feedback, demo videos). Currently in engineering preview. Intro | Github  | Free |
| QM | YC open-source multi-agent harness for organizations. Runs on Slack and Web with scoped workspaces (memory, files, credentials, permissions) per employee/project/channel; headless core with replaceable models/harnesses and self-hostable via Docker/Fly/AWS. Intro | Github  | Free |
| Buzz | Open-source, self-hostable workspace where humans and AI agents share the same rooms. Agents get their own keys and audit trail to open repos, send patches, review code, run workflows, edit canvases, and join voice huddles. Built on a Nostr relay so every message and action is a signed event. Intro | Github  | Free |
| deer-flow | ByteDance's open-source long-horizon SuperAgent harness. Orchestrates sub-agents, memory, sandboxes, tools, skills, and message gateways to research, code, and create. Built on LangGraph/LangChain with a web UI and multi-provider LLM support. Intro | Github  | Free |
| Orkas | Open-source, local-first multi-agent AI desktop client. A Commander decomposes goals and coordinates specialist agents in parallel or sequence, with private skills and memory. Supports BYO model providers and local model endpoints, and can drive Claude Code, Codex, OpenClaw, OpenCode, and Hermes. Cross-platform (macOS / Windows / Linux). | Website Github  | Free |
| Orca | Cross-platform Agent Development Environment (ADE) for orchestrating fleets of parallel AI coding agents. Run Claude Code, Codex, OpenCode, Pi, and any CLI agent side-by-side in isolated git worktrees, compare outputs, and merge the winner. Features mobile companion, terminal splits, Design Mode for capturing Chromium UI elements, GitHub/Linear integration, SSH worktrees, AI diff annotations, and Computer Use. Intro | Website Github  | Free |
| AgentsMesh | The AI Agent Workforce Platform. Self-hostable remote AI workstations (AgentPods) with PTY sandbox + git worktree isolation, multi-agent collaboration via channels and pod bindings, built-in Kanban with MR/PR integration, per-pod MCP server. Supports Claude Code, Codex CLI, Gemini CLI, Aider, OpenCode. | Github  | Free (BSL-1.1) |
| microsoft/autogen | AutoGen is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks. | Github  | Free |
| msitarzewski/agency-agents | Open-source AI agency toolkit with 230+ specialized agent personas across engineering, design, marketing, sales, finance, game dev, healthcare, and more. Features ready-to-use agent personalities, workflow templates, deliverables, and a native desktop app to browse/install agents into Claude Code, Cursor, Codex, Gemini, Kimi Code, Aider, and other AI dev tools. Intro | Github  | Free |
| ECC | Open-source enhancement framework for AI coding agents. Unified agent/skills/rules/Hooks/MCP configuration across Claude Code, Codex, Cursor, OpenCode, Gemini, Zed, GitHub Copilot. Ships with 60 sub-agents, 232 skills, persistent memory, AgentShield security scan, and desktop dashboard GUI. | Github  | Free |
| CC Switch | Cross-platform desktop app to manage Claude Code, Codex, Gemini CLI, OpenCode, and OpenClaw. Features visual configuration for API providers, MCP servers, and skills with bidirectional sync. Intro | Github  | Free |
| codex-plugin-cc | Claude Code plugin that enables using OpenAI Codex for code reviews and task delegation directly within Claude Code workflow. Provides /codex:review, /codex:adversarial-review and other commands | Github  | Free |
| codesight | CLI token optimizer and AI context generator with built-in MCP server. Scans codebases to extract routes, schema, components, and dependencies, reducing AI context tokens by 9x–13x. Profiles for Claude Code, Cursor, Copilot, Codex, and Windsurf. Zero runtime dependencies. | Github  | Free |
| AGENTS.md | An open standard for codebase documentation designed specifically for AI coding agents. Provides structured context, instructions, and constraints to help agents work more effectively and safely. Intro | Github  | Free |
| Spec Kit | GitHub's open-source toolkit for Spec-Driven Development (SDD). Provides the specify CLI and slash commands (/speckit.specify, /speckit.plan, /speckit.implement, etc.) that integrate with 30+ AI coding agents to turn specifications into executable implementation plans. | Github  | Free |
| musistudio/claude-code-router | A powerful tool to route Claude Code requests to different models and customize any request. Supports multi-provider routing, request/response transformation, dynamic model switching, CLI model management, and GitHub Actions integration. | Github  | Free |
| instructkr/claw-code | A reimplementation of Anthropic's Claude Code agent harness, currently being rewritten in Rust for memory safety. Focuses on building a better tool harness for AI agents with legal/ethical reimplementation | Github  | Free |
| MemPalace | Open-source AI memory system that stores full conversations and project data locally without cloud dependencies. Organizes memories into a hierarchical "palace" structure, achieves 96.6% recall on LongMemEval benchmarks (highest scoring), supports MCP integration and works offline with local LLMs. | Github  | Free |
| TencentDB Agent Memory | Tencent Cloud's open-source memory infrastructure for agent teams. Provides Memory Hub for cross-session/cross-agent memory sharing, Chat Memory with L0–L3 distillation, Skill library for reusable expertise, and Wiki/CodeGraph for docs/code knowledge maps. Works with Claude Code, CodeBuddy, and other agents. Intro | Github  | Free |
| Hermes Agent | Open-source agentic framework built by NousResearch, fine-tuned on Hermes models with strong tool calling and reasoning capabilities for building autonomous AI agents. | Github  | Free |
| Screenpipe | Searchable screen-text and audio history for recall, meeting notes, and work summaries via MCP or a local API. Raw history stays local by default; configured cloud AI, transcription, sync, and integrations can process context off-device. Source-available under the Screenpipe Commercial License. macOS, Windows, and Linux. | Github  | Limited free plan; paid subscriptions |
| MastraAI | Mastra is an opinionated TypeScript framework that helps you build AI applications and features quickly. It gives you the set of primitives you need: workflows, agents, RAG, integrations and evals | Github  | Free |
| FlowGram.AI | An extensible visual AI workflow development framework with built-in canvas, form engine, variable scope chain, and ready-to-use materials (LLM, Condition, Code Editor, etc.) for building AI workflow platforms faster. | Github  | Free |
| Conductor | Netflix-originated open-source durable workflow engine now focused on AI agent orchestration. Provides event-driven execution, durable state, retries/timeouts, 14+ LLM providers, MCP tool calling, function calling, human-in-the-loop approval, and vector DB integration for RAG. Trusted in production at Netflix, Tesla, LinkedIn, and J.P. Morgan. Intro | Github  | Free |
| DeepTutor | An agent-native learning workspace by HKUDS that unifies AI tutoring, problem solving, quiz generation, research, visualization, and mastery practice. Features multi-engine RAG, persistent memory, Partners/My Agents, and live coding CLI integration. Intro | Github  | Free |
| potpie-ai/potpie | Open Source AI Agents for your codebase in minutes. Use pre-built agents for Q&A, Testing, Debugging and System Design or create your own purpose-built agents. | URL , Github  | Free Trial |
| agentscope | Agent-Oriented Programming for Building LLM Applications, Open-sourced by Alibaba | Github | Free |
| Auto-GPT | Open source, An experimental open-source attempt to make GPT-4 fully autonomous. | GitHub <br>  | Free |
| CLI-Anything | An open-source frame |
Discussion
No comments yet — start the thread.
Sign in to join the discussion.