Prompt Flow: Microsoft's Engineering Discipline for LLM Apps - Inside microso...
Prompt Flow is Microsoft’s answer to a question every team eventually asks: what would it look like if LLM application development had the same engineering discipline as ordinary software? The README defines it as “a suite of development tools designed...
Ollama: How the Local Model Runner Puts an LLM on Every Machine - Inside olla...
Ollama is the tool that made running open models a one-line command, and it is now a standard piece of developer infrastructure: install it with curl -fsSL https://ollama.com/install.sh | sh on macOS or Linux, irm https://ollama.com/install.ps1 | iex on Windows,...
Open Interpreter: Reborn as a Rust Coding Agent for Cheap Models - Inside ope...
If you remember Open Interpreter as the Python project that let a language model loose in your terminal, the current repository will surprise you. The README now introduces “a coding agent optimized for low-cost models,” and the source is a...
LlamaIndex: The Data Framework That Taught LLMs to Read Your Files - Inside r...
LlamaIndex is the framework that made “connect your data to an LLM” a teachable, layered discipline rather than a pile of glue scripts. Its monorepo at run-llama/llama_index is MIT-licensed Python organized with unusual clarity: llama-index-core holds the abstractions, llama-index-integrations holds...
LangChain: The Agent Engineering Platform From the Inside - Inside langchain-...
LangChain describes itself as “the agent engineering platform,” and the monorepo backs the branding with real architecture: an MIT-licensed Python framework whose core abstraction, the Runnable, lets models, prompts, tools, parsers, and retrievers compose into applications with the pipe operator,...
gpt-engineer: The OG Code Generation Platform - Inside gpt-engineer-org/gpt-e...
gpt-engineer calls itself “the OG code generation experimentation platform,” and the README is refreshingly honest about what it wants to be: not a polished product but a laboratory where coding-agent builders can specify software in natural language, watch an AI...
Flowise: Building the Visual Agent Factory - Inside FlowiseAI/Flowise
Flowise taught a generation of developers that you could build LLM applications the way children build with blocks: drag a node, draw a line, press play. The repository at FlowiseAI/Flowise is a TypeScript monorepo that grew into one of the...
Dify: The LLM App Platform Where Workflows Meet Production - Inside langgeniu...
Dify describes itself as an open-source LLM app development platform, and unlike many projects that use that phrase loosely, it really is a platform: a Next.js console for building, a Python backend that serves chat, completion, agent, and workflow applications,...
CrewAI: Role-Playing Agent Teams as a Framework - Inside crewAIInc/crewAI
CrewAI made its name on a simple, sticky metaphor: put a crew of role-playing agents on a job, give each one a role, a goal, and a backstory, and let them work tasks in sequence or under a manager. The...
AutoGen: The Multi-Agent Framework That Taught Agents to Talk - Inside micros...
AutoGen is the Microsoft Research project that made “agents talking to agents” a mainstream engineering pattern, and its second generation is a genuinely well-engineered codebase: MIT-licensed Python split into a core runtime, an AgentChat layer for everyday use, an extensions...
Tabby: A Self-Hosted Copilot on Your Own GPU - Inside TabbyML/tabby
GitHub Copilot popularized AI code completion, but it also taught a generation of developers an uncomfortable lesson: your code leaves your machine. Tabby, built by TabbyML in Rust under an open source license, is the counter-argument - a self-hosted AI...
SWE-Agent: An Agent-Computer Interface for Fixing Real GitHub Issues - Inside...
SWE-agent is the open source project that turned a research question into a benchmark-beating system: what interface should you give a language model so it can actually fix bugs in real repositories? Built by researchers from Princeton and Stanford and...
OpenCode: The Terminal-Native AI Coding Agent With No Vendor Lock - Inside an...
OpenCode brands itself “the open source AI coding agent,” and the repository backs the claim with unusual breadth: it started as the agent from the SST team, it is now maintained under the anomalyco organization, and a single install command,...
Goose: The Off-the-Leash AI Agent You Can Script - Inside aaif-goose/goose
Goose is an AI agent that runs tasks on your machine, and its history makes it worth studying: it started at Block, the payments company, as an engineer’s coding and operations assistant, and it now lives with the Agentic AI...
Gemini CLI: Google's Open Source Terminal Agent - Inside google-gemini/gemini...
Gemini CLI is Google’s open source AI agent that lives in your terminal, and it arrives with a proposition that is hard to ignore: run npx @google/gemini-cli and you get the Gemini models, with a free tier of 60 requests...
Continue: One Engine for IDE and CLI Coding Agents - Inside continuedev/continue
Before AI coding assistants consolidated into single-vendor products, Continue was one of the projects that proved an open source alternative could match them: the same agent engine available in VS Code, JetBrains, and the terminal, connected to whichever model you...
Codex: OpenAI's Local Coding Agent in Rust - Inside openai/codex
Codex is OpenAI’s coding agent, and unlike most products from the company it is fully open source under Apache-2.0, with its entire engine readable in the repository. The agent runs locally on your machine: it reads your code, proposes and...
Cline: One Agent Core for IDE, Terminal, and Hub - Inside cline/cline
Cline started life as a VS Code extension and grew into one of the most popular open source coding agents, and its repository has now been rebuilt into something bigger: a layered TypeScript monorepo where one agent core serves an...
Aider: AI Pair Programming in Your Terminal - Inside Aider-AI/aider
Most AI coding assistants live in a browser tab or an IDE plugin, but the most productive place for many developers is still the terminal, right next to git. Aider, maintained by Aider-AI under the Apache-2.0 license, is a Python...
OpenHands: Agent Canvas, a Control Center for Coding Agents - Inside All-Hand...
The first wave of AI coding tools gave every agent its own window; the next wave is about orchestration. OpenHands, one of the most recognized names in open source coding agents, has evolved its flagship repository into Agent Canvas, which...
Trape: Real-Time People Tracking as a Research Lens - Inside jofpin/trape
Few security tools announce their intent as plainly as Trape. The subtitle on the repository reads “People tracker on the Internet: Learn to track the world, to avoid being traced,” and the project — created by Jose Pino, presented at...
Traccar: 272 Protocol Decoders on a Netty Bus - Inside traccar/traccar
Traccar is the engine room of the GPS tracking world: a free, Apache-2.0 licensed Java back-end that speaks to more than two hundred device protocols and two thousand tracking device models out of the box, from fleet trackers to phone...
TaskTrooper: Put It on the Board, the Agents Ship It - Inside makifbaysal/tas...
Agent CLIs like Claude Code, Cursor, Antigravity, and OpenCode are superb at doing work you hand them, one task at a time. What they do not do is coordinate a whole software team’s worth of work: decide what ships next,...
SpiderFoot: 234 Modules Over One Event Queue - Inside smicallef/spiderfoot
Give SpiderFoot a domain, an IP address, an email, or even a bitcoin address, and it does the rest: hundreds of small Python modules wake up, trade findings with each other, and gradually assemble a map of everything publicly connected...