OPEN SOURCE
150 items
123 posts, 27 tools
Free, open-source (Apache-2.0) AI agent built in Rust, governed by the Agentic AI Foundation. Desktop app, CLI, and API. Bring any of 15+ model providers or an existing subscription.
Open-source AI gateway: call 100+ LLM providers in the OpenAI format via a Python SDK or proxy. Spend tracking, budgets, rate limiting, load balancing, and fallbacks built in.
Open-source LLM engineering platform: tracing, evals, prompt management, and datasets. Self-hostable, OpenTelemetry-native, with 50+ framework integrations.
Open-source cloud sandboxes that run each AI agent session in its own microVM. Isolated environments that start in under 200ms, run code in Python, JavaScript, and more, and persist sessions up to 24 hours.
DiffusionGemma is Google's 26B MoE open model that generates 256-token blocks in parallel. What diffusion generation means for latency and local inference.
Mastra review and setup for TypeScript AI agents - verified create commands, Mastra Studio, workflows and memory, plus pricing and who should skip it.
The rsync Claude debate shows why teams need reproducible defect forensics before AI attribution becomes a public blame machine.
Forge makes small local models more reliable at tool-calling with a harness that catches structural failures, retries intelligently and controls context.
Cline is a free, open-source VS Code extension for agentic AI coding. Bring your own model, a cloud API or a local one via Ollama, with no vendor lock-in.
The trending Free Claude Code repo is not just about avoiding API bills. It points at a bigger developer-tool pattern: model gateways for AI coding agents.
jcode is trending because it competes on a less glamorous but important agent metric: how cheap it is to keep many coding sessions alive.
Microsoft's lib0xc makes existing C code safer with static bounds, checked integer conversions, and strict warnings - incremental hardening, not a rewrite.
Hugging Face's ml-intern is a domain agent for ML work - papers, datasets, training jobs, and Hub traces. Why domain tools beat generic chat for coding agents.
Warp open sourced its terminal client. The bigger story is agent operations - planning, execution, review, and feedback loops that live next to the shell.
DeepSeek V4 developer guide: Flash vs Pro, pricing, OpenAI SDK setup with thinking mode and tool calling, and when to pick V4 over Claude or GPT.
Nemotron 3 Super developer guide: the latent MoE hybrid Mamba architecture, hardware needs, reasoning modes, and code to run NVIDIA's 120B model.
The open-source MCP servers worth a permanent slot in your config, each with what it does, why it matters, and copy-paste setup for Claude Code and Cursor.
Claude Design skills broke out on GitHub as four repos trended in one week. What huashu-design, open-codesign, and cc-design do, and why the pattern matters.
Alibaba's open-weight coding model, released in 2025. 480B total parameters, 35B active (MoE). Native 256K context, extends to 1M. Apache 2.0 license. Built for agentic coding.
DeepSeek's reasoning-first model built for agents. First model to integrate thinking directly into tool use. Ships alongside V3.2-Speciale, which rivals GPT-5 and Gemini 3.0 Pro.

Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.