Tools

A cat clone with wings

Modern replacement for the Unix cat command with syntax highlighting for 200+ languages, automatic paging, line numbers, Git integration showing file modifications, and themes including integration with terminal color schemes. Supports plain text output mode for piping. Extremely fast with Rust-based implementation. Can be used as a drop-in cat replacement via aliasing. 51K+ GitHub stars. Part of the modern CLI toolkit alongside fd, ripgrep, and eza.

AI chatbot framework for WeChat with multi-model and plugin support

chatgpt-on-wechat is an open-source framework for deploying AI chatbots on WeChat, the dominant messaging platform in China. It supports OpenAI, Claude, Gemini, Qwen, and local models through a plugin architecture. Features group chat management, image generation, voice messages, and knowledge base integration. Over 42,700 GitHub stars reflecting massive adoption in the Chinese developer community.

Resume interrupted CLI agent sessions

Session persistence tool for terminal-based AI coding agents that saves full agent context and lets you resume seamlessly after interruptions — network drops, timeouts, or intentional breaks. Works with popular AI CLI agents and maintains conversation history, file states, and task progress across sessions. Particularly valuable for long-running agentic tasks that span hours or multiple work sessions.

CLI tool to convert codebases into LLM-ready prompts

code2prompt is a Rust CLI that converts entire codebases into structured prompts optimized for LLM context windows. It intelligently filters files using gitignore patterns, respects token budgets, generates directory tree visualizations, and supports custom Handlebars templates for output formatting. The tool addresses the core challenge of feeding large codebases to AI coding assistants by producing clean, organized context that maximizes the value of limited token budgets.

Developer news aggregator

Curated developer news platform that replaces your browser's new tab with a personalized feed of technical articles, releases and discussions drawn from 1,300+ engineering sources. Smart ranking surfaces content that matches the languages and tools you follow, while Squads let specialized communities discuss frameworks, careers and releases in the open. The fastest way to stay current without building and maintaining a private RSS habit.

SQL-based data transformation framework

dbt (data build tool) is an open-source SQL transformation framework with 10K+ GitHub stars that lets analytics engineers transform data in their warehouse using select statements. Brings software engineering practices to data — version control, testing, documentation, and CI/CD for SQL. Supports Snowflake, BigQuery, Redshift, Databricks, PostgreSQL, and more. Features Jinja templating, incremental models, snapshots, and a package hub of reusable transformations.

Nix-powered reproducible development environments

devenv uses Nix to create reproducible, declarative development environments that work consistently across machines. Define project dependencies, services, environment variables, and pre/post hooks in a single devenv.nix file. Supports automatic shell activation, process management for databases and services, and integration with direnv for seamless directory-based environment switching.

Python library for declarative data loading that LLMs can generate

dlt (data load tool) is a Python library for building data pipelines with declarative, schema-aware loading that is simple enough for LLMs to generate correctly. It extracts data from APIs, databases, and files, normalizes nested structures, handles schema evolution, and loads into warehouses and lakes. Supports 30+ destinations including BigQuery, Snowflake, DuckDB, and PostgreSQL. Over 5,200 GitHub stars.

Infrastructure as Code orchestration and governance platform

env0 is an IaC orchestration platform that manages Terraform, OpenTofu, Pulumi, and CloudFormation workflows with built-in governance, cost estimation, and drift detection. It provides self-service infrastructure provisioning with policy guardrails, automated plan approvals, and budget controls. Supports custom deployment flows with OPA-based policy enforcement and RBAC.

Modern lodash alternative with TypeScript

es-toolkit is a modern JavaScript utility library by Korean fintech Toss, built as a high-performance Lodash replacement. With TypeScript-first design and full tree-shaking support, it cuts bundle sizes by up to 97 percent. Provides utility functions for arrays, objects, strings, and async operations with 2-3x better runtime performance. Includes an es-toolkit/compat layer for seamless migration from Lodash without rewriting existing codebases.

Ultra-fast JavaScript bundler written in Go

esbuild is a JavaScript bundler written in Go with 38K+ GitHub stars that runs 10-100x faster than traditional bundlers like Webpack. Handles JavaScript, TypeScript, JSX, CSS bundling, and minification with near-instant build times. Used as the build engine inside Vite for production builds. Features tree shaking, code splitting, source maps, and a plugin API. Minimal configuration required — most projects need zero config files. Single binary with no JavaScript dependencies.

Filesystem-first framework for durable AI agents

Eve is Vercel's filesystem-first TypeScript framework for building durable AI agents as ordinary project files. It combines Markdown instructions and skills, typed tools, channels, connections, subagents, schedules, sandboxes, and evals with Vercel's agent runtime so teams can ship deployable agents without hand-rolling orchestration. The current beta fits Vercel-native backend agent projects.

Modern replacement for ls

Modern replacement for the Unix ls command written in Rust with color-coded output, Git integration showing file status, tree view, icon support, extended attributes display, and hyperlink support for terminals. Faster than ls with features like recursive directory listing, grid/long/tree layouts, and filtering by file type. Maintained fork of the discontinued exa project. Part of the modern CLI toolkit alongside bat, fd, ripgrep, and zoxide. 14K+ GitHub stars.

Serverless AI inference for generative media at scale

fal.ai is a serverless AI inference platform providing ultra-low-latency APIs for generating images, videos, audio, and 3D models. With 600+ production-ready models and native Python and JavaScript SDKs, it eliminates GPU management while delivering 30-50% lower costs than alternatives. Automatic scaling with no cold starts and real-time streaming support make it ideal for interactive AI applications.

Simple, fast alternative to find

Fast, user-friendly alternative to the Unix find command written in Rust. Features intuitive syntax, colorized output, regex and glob pattern support, smart case sensitivity, parallel execution, and automatic .gitignore respect. Significantly faster than find for most use cases. Integrates well with other tools via piping. Part of the modern CLI toolkit alongside ripgrep, bat, eza, and fzf. 35K+ GitHub stars.

Fastest file search toolkit for AI agents and Neovim

fff.nvim (freakin fast fuzzy) is a high-performance file search toolkit for AI agents, Neovim, Rust, C, and NodeJS. Hybrid architecture with Lua frontend and Rust backend delivers sub-10ms search across 50K+ file codebases. Uses frecency memory combining frequency, recency, git status, and definition matches to surface the most relevant files for AI coding workflows.

Command-line fuzzy finder

General-purpose command-line fuzzy finder written in Go that adds interactive filtering to any list — files, command history, processes, Git branches, and more. Blazing fast even on millions of entries. Integrates with bash, zsh, fish, and vim/neovim for history search (Ctrl+R), file finding, and directory jumping. Supports preview windows, multi-select, and custom key bindings. 67K+ GitHub stars. One of the most essential CLI productivity tools in the modern developer toolkit.

Google's application kernel for container sandboxing and security

gVisor is Google's open-source container runtime sandbox that provides an additional layer of isolation between containerized applications and the host kernel. It implements a user-space application kernel that intercepts system calls, preventing container escapes and limiting the attack surface. Used in Google Cloud Run, GKE Sandbox, and other Google Cloud services. Over 18,000 GitHub stars.

NVIDIA's LLM vulnerability scanner and red-teaming tool

garak is NVIDIA's open-source LLM vulnerability scanner for red-teaming AI models and applications. Probes for prompt injection, data leakage, hallucination, toxicity, encoding-based attacks, and dozens of other vulnerability categories. Runs automated attack sequences against any LLM endpoint and generates detailed vulnerability reports. Features a modular probe/detector architecture that is extensible with custom attack patterns. Named after the Star Trek character known for deception.

Lightweight C++ inference for Google Gemma models

gemma.cpp is Google's standalone C++ inference engine built specifically for running Gemma language models without Python or CUDA dependencies. It provides optimized CPU inference using SIMD instructions and Highway library, supports Gemma 2 and Gemma 3 models, and runs on x86 and ARM architectures. Designed for embedded systems, edge devices, and server deployments needing minimal overhead.

One-command local coding agent that auto-detects your hardware and picks the best model

hf-agents is a Hugging Face CLI extension that detects your hardware, recommends the best GGUF model using llmfit, and launches a local coding agent in a single command. It collapses the multi-step local LLM setup into hf agents run pi, automatically handling hardware profiling, model download, inference server startup, and coding agent activation.

Header-only C++ implementation of HNSW for fast approximate nearest-neighbor search.

hnswlib is a header-only C++ library implementing the Hierarchical Navigable Small World (HNSW) graph algorithm for approximate nearest-neighbor search, with Python bindings and a tiny dependency footprint. Originally developed by the nmslib team, it has become the default HNSW implementation embedded inside many vector databases and search products. Engineers use it directly when they want HNSW retrieval without pulling in a heavyweight vector DB.

Open-source diagnostic for AI operational misalignment

iFixAi is an Apache-2.0 diagnostic tool for scoring AI agents and models against operational-misalignment risks such as hallucination, manipulation, sabotage, sandbagging, and oversight evasion.

macOS terminal replacement

Feature-rich terminal emulator for macOS that has been the de facto standard for Mac power users and developers for over a decade. Supports split panes, tabs, profiles, triggers, hotkey windows, search with regex, shell integration for marks and navigation, tmux integration, and extensive customization via JSON profiles. Built-in password manager, automatic profile switching based on context, and Python scripting API for automation. Free and open-source with a loyal community.

Zero-friction single-binary Kubernetes distribution by Mirantis

k0s is a lightweight, CNCF-certified Kubernetes distribution packaged as a single binary with zero host dependencies. Backed by Mirantis, it simplifies cluster deployment by bundling all required components into one executable that works on any Linux system. Supports x86-64, ARM64, and ARMv7 architectures with automatic upgrades and a built-in control plane load balancer.

Lightweight Kubernetes distribution for edge, IoT, and development

k3s is a CNCF Sandbox lightweight Kubernetes distribution packaged as a single binary under 100MB. Created by Rancher Labs and now maintained by SUSE, it strips non-essential components and bundles containerd, Flannel, CoreDNS, and Traefik into a minimal but fully conformant K8s distribution. Ideal for edge computing, IoT, ARM devices, and local development environments.

Modern load testing for developers

k6 is an open-source load testing and performance testing tool developed by Grafana Labs. Developers write performance tests in JavaScript and execute them on a high-performance Go runtime capable of generating thousands of virtual users per machine. Features a CLI-first workflow, cloud-based test execution, and integrations with Grafana dashboards — making performance testing as accessible as writing unit tests.

The fast, feature-rich terminal

GPU-accelerated terminal emulator written in C and Python, focused on performance and features. Supports ligatures, true color, graphics protocol for displaying images/plots inline, tabs, splits, and remote control via IPC. Highly configurable via a plain text config file. Cross-platform on macOS and Linux. Features a kitten framework for writing terminal programs in Python. Known for innovation in terminal graphics. 26K+ GitHub stars and a dedicated power-user community.

Git-like version control for data lakes and object storage

lakeFS is an open-source platform that brings Git-like branching, committing, and merging to data lakes and object storage. It works on top of S3, GCS, Azure Blob, and MinIO, enabling teams to create isolated data branches for experimentation, run CI/CD for data pipelines, and maintain full data lineage. Acquired DVC in 2025, uniting data version control for both small and enterprise-scale workloads.

AI agent skill that researches topics across social platforms and web

last30days-skill is an agent skill for Claude Code and other AI coding agents that researches topics by scanning social platforms, news sites, and web sources from the past 30 days. It aggregates recent discussions, launches, and community sentiment into actionable research summaries. With 17,400 GitHub stars and MIT license, it has become one of the most popular agent skills in the emerging ACP ecosystem.

Terminal UI for Docker

Terminal UI for Docker and Docker Compose that provides an interactive dashboard for managing containers, images, volumes, and networks without memorizing CLI commands. Features real-time logs, stats (CPU/memory), container shell access, bulk cleanup of unused resources, and Docker Compose service management. Navigate with keyboard shortcuts in a panel-based layout. By the creator of lazygit. 40K+ GitHub stars. The fastest way to manage Docker from the terminal.

Simple terminal UI for git

Terminal-based Git UI that provides an intuitive, interactive interface for Git operations without memorizing commands. Features staging/unstaging hunks and lines, interactive rebase with drag-and-drop, conflict resolution, commit graph visualization, cherry-picking, branch management, stash operations, and custom commands. Navigate with keyboard shortcuts in a panel-based layout. Integrates with your existing Git config. 55K+ GitHub stars. The go-to TUI for Git users who prefer the terminal.

Hot-swap between local LLM models via OpenAI-compatible API

llama-swap is an open-source tool that manages multiple local LLM models behind a single OpenAI-compatible API endpoint. It automatically loads and unloads models on demand, letting developers hot-swap between different models without restarting services. With 3.1K+ GitHub stars, it solves the common pain point of running multiple specialized models on limited hardware.

High-performance local LLM inference in C/C++

llama.cpp is the foundational C/C++ library with 75K+ GitHub stars powering local LLM inference on consumer hardware. Provides optimized CPU and GPU inference for quantized models in GGUF format. Supports LLaMA, Mistral, Phi, Gemma, and most open-weight families. Features 2-8 bit quantization for reduced memory, multi-GPU support, context extension, grammar-constrained output, and an OpenAI-compatible API server. The engine behind Ollama and LM Studio.

Kubernetes-native distributed LLM inference stack

llm-d is an open-source Kubernetes-native stack for distributed LLM inference with cache-aware routing and disaggregated serving. It separates prefill and decode stages across different GPU pools for optimal resource utilization, routes requests to nodes with warm KV caches, and integrates with vLLM as the serving engine. Apache-2.0 licensed with 2,900+ GitHub stars.

Find which AI models actually run on your hardware in one command

llmfit is a Rust-based terminal tool that matches over 200 LLM models from 30+ providers against your exact hardware specs. The interactive TUI scores each model on fit, speed, VRAM usage, and context length, helping you avoid downloading models that won't run on your machine. It supports Ollama, llama.cpp, MLX, Docker Model Runner, and LM Studio backends.

Composable agent orchestration via MCP servers

mcp-agent is an open-source framework with 8K+ GitHub stars for building AI agents that leverage MCP (Model Context Protocol) servers as composable tool providers. Agents connect to multiple MCP servers simultaneously, gaining access to diverse capabilities without custom integrations. Supports multi-agent workflows, parallel tool execution, and automatic server discovery. Designed to make MCP the universal interface between AI agents and external tools, databases, and services.

Protocol bridge converting MCP stdio transport to HTTP/SSE endpoints

mcp-proxy is a protocol bridge that converts MCP servers using stdio transport into HTTP and Server-Sent Events endpoints accessible over the network. This enables remote MCP server hosting, load balancing, and sharing servers across multiple AI clients. Supports both directions: wrapping stdio servers with HTTP and connecting to remote SSE servers through local stdio. Over 2,400 GitHub stars.

Fullstack MCP framework connecting any LLM to MCP servers

mcp-use is an open-source framework that enables any LLM to interact with MCP servers through a unified client interface. It bridges the gap between models that lack native MCP support and the growing ecosystem of MCP tools by providing automatic tool discovery, execution management, and multi-server orchestration. Supports both direct LLM connections and agent-based workflows. Over 9,000 GitHub stars.

Hosted MCP server platform

Platform for running MCP servers securely in WebAssembly sandboxes. One-click install for Claude Desktop, VS Code, and other MCP-compatible clients with no Docker required. Simplifies MCP server deployment and management by handling isolation, security, and distribution, making it easy to extend AI assistants with custom tools without infrastructure overhead.

Turn any MCP server, OpenAPI spec, or GraphQL endpoint into a CLI — at runtime, with zero codegen.

mcp2cli turns MCP servers, OpenAPI specs, and GraphQL endpoints into standard CLIs at runtime — no codegen, no schema bloat. Tools and arguments load only when requested via --list and --help flags, cutting up to 96–99% of the tokens that native MCP integrations waste on schema preloading. Works with Claude Code, Cursor, Codex, and any agent that can call shell commands, and ships with OAuth, stdio/HTTP/SSE transports, and a bake mode for reusable connections.

The 100-line SWE agent that solves GitHub issues from your terminal

Radically minimal open-source SWE agent (~100 lines of Python) that uses nothing but bash to fix GitHub issues and assist in the command line, while scoring >74% on SWE-bench Verified.

Run local code inside your Kubernetes cluster without deploying

mirrord lets developers run local processes as if they were inside their Kubernetes cluster — intercepting network traffic, environment variables, and file access at the OS level without any deployment or configuration changes. Backed by $12.5M in seed funding with investors including Sentry's co-founder, it claims up to 98% faster iteration cycles and 30% fewer production bugs by eliminating the gap between local and cluster environments.

Polyglot dev tool version manager replacing asdf, nvm, pyenv

mise is a Rust-based polyglot development tool version manager that replaces asdf, nvm, pyenv, rbenv, and similar single-language version managers with one fast CLI. It manages runtime versions for Node.js, Python, Go, Rust, Terraform, and 900+ other tools from a single .mise.toml config file. mise also serves as a task runner with file watching, environment variable management, and monorepo support, making it a complete developer environment orchestrator with over 26,000 GitHub stars.

LSP-based AI code review agent backed by Y Combinator

mrge is a YC-backed AI code review agent that uses Language Server Protocol analysis to provide deep, context-aware pull request reviews. It goes beyond surface-level pattern matching by understanding project structure, type information, and cross-file dependencies. Integrates with GitHub and GitLab to deliver automated reviews that catch logic errors, security issues, and architectural inconsistencies.

ModelScope's fine-tuning framework supporting 600+ models

ms-swift is ModelScope's open-source framework for fine-tuning over 600 large language and multimodal models. It supports SFT, DPO, RLHF, LoRA, QLoRA, and full fine-tuning with a web UI and CLI interface. Optimized for the Chinese AI ecosystem with native ModelScope Hub integration alongside Hugging Face support. Over 13,500 GitHub stars.

Community MCP server for n8n node knowledge, workflow drafting, and validation

n8n-MCP is an independent, MIT-licensed community server that gives MCP-compatible assistants structured access to n8n node documentation, properties, templates, and workflow validation helpers. It is distinct from the existing n8n product page and covers the MCP layer used from clients such as Claude, Cursor, Windsurf, and Codex.

AI data IDE for 10x faster data work

nao is an open-source, Y Combinator-backed analytics agent framework for building and deploying AI-powered analytics assistants that query data, generate insights, and interact with data warehouses through natural language. Makes data analysis accessible to non-technical users with a framework where developers expose tables, metrics, and semantic layers — then the agent answers business questions in plain English with SQL and visualizations.