Coding
Pair programmers, autocompletes, and agentic code editors.
70 tools
Every developer is now an AI-assisted developer. The split is between in-line autocompletes, AI-first IDEs, and full agents that write commits and open PRs.
Includes IDE-integrated pair programmers (Cursor, Copilot, Codeium), CLI/terminal agents (Aider), and full autonomous coding agents (Devin, Replit Agent).
Pick an AI-first IDE (Cursor) for daily coding. Pick Copilot if you're standardised on JetBrains/VS Code already. Pick a coding agent (Devin, Replit Agent) for greenfield prototyping or ticket-grade work.
oMLX
Native macOS LLM inference server built on MLX, with paged SSD KV caching for Apple Silicon agents.
DeepSeek
Chinese AI lab shipping open-weight reasoning models that punch well above their API price.
OpenRouter
Unified API gateway to 400+ LLMs from 70+ providers, with one OpenAI-compatible endpoint and automatic failover.
omp (Oh My Pi)
Open-source terminal coding agent with LSP, DAP, subagents, and a native Rust execution engine.
AI SDK
Vercel's open-source TypeScript framework for building AI apps across 16+ providers with unified streaming, tools, and UI hooks.
Beam
Serverless GPU infrastructure for AI workloads with sub-second cold starts and bring-your-own-cloud support.
HTML Anything
Agentic HTML editor that turns markdown, CSV, and JSON into ship-ready posts for WeChat, X, Zhihu, and Xiaohongshu.
Keploy
Open-source AI testing platform that records real API traffic and replays it as regression tests in CI.
Kilo Code
Open-source agentic coding assistant for VS Code, JetBrains, and the terminal with bring-your-own-key routing across 500+ models.
LLM by Datasette
A CLI and Python library for running prompts against any LLM provider and logging everything to SQLite.
Ollama
The de facto runtime for running open-weights LLMs locally, now with a paid cloud tier for bigger models.
Pieces
On-device long-term memory layer that feeds your last nine months of work context into any LLM or IDE assistant.
Qodo (formerly CodiumAI)
AI code review and test generation platform that plugs into IDEs, pull requests, and CLI with deep multi-repo context.
Recommenders
Open-source Python library with classical and deep-learning algorithms for building recommendation systems.
Apache Mahout
Open-source ML framework pivoting toward scalable quantum computing primitives.
Capacity
AI app builder that generates full-stack React + Express + SQLite apps from natural language specs.
Groq
Custom-silicon LPU inference platform serving open models at GPU-trouncing latency via an OpenAI-compatible API.
PandasAI
Conversational data analysis library that turns natural-language questions into pandas, SQL and chart code.
Runcell
Jupyter-native AI agent built for multi-week ML and data science projects.
StarOps
AI-native platform engineering engine that provisions and manages cloud infrastructure from natural-language prompts.
AI2sql
Natural-language-to-SQL generator with desktop app, MCP server, and governed read-only access.
Amazon Q Developer
AWS's in-IDE coding assistant and agent, formerly CodeWhisperer, tuned for cloud-heavy workflows.
Code to Flow
AI-powered converter that turns code snippets into flowcharts, sequence diagrams, and class diagrams.
CodeRabbit
AI pull-request reviewer that lives inside GitHub, GitLab, and your IDE.