AI APIs, developer tools, SDKs and technical releases.
AI developer news covers the APIs, SDKs, open-source models, and infrastructure that engineers actually build with. Expect coverage of OpenAI Assistants API, Anthropic tool use, Hugging Face model drops, LangChain and LlamaIndex releases, vector databases, and the fast-moving world of open-weights models (Llama, Mistral, Qwen, DeepSeek).
If you build AI features into your product, this feed tells you which primitives just got faster, cheaper, or better — and which open models are now good enough to self-host.
Turn any OpenAPI REST API into an MCP server so AI agents can call it — a focused, production-ready CLI with zero runtime dependencies

Türkiye aims to shape global AI standards and grow domestic exports by signing framework agreements with at least five countries and memoranda of understanding with three international institutions by late 2027.

TSMC is sharpening its silicon photonics (SiPh) roadmap to address the widening gap between AI compute growth and chip-to-chip data movement, unveiling two bandwidth-scaling paths for its next-generation COUPE platform and outlining a broader role for heterog…
Headless MCP server for Screaming Frog SEO Spider: run crawls, export and analyze crawl data via the CLI, no GUI session required. Built for scheduled audits, CI, and AI agents.
An integration of Anthropic Claude models into the Haystack framework.
LangChain integration for SafePrompt — prompt-injection detection as a callback handler. Validates every prompt flowing through a chain before it reaches the LLM.
A library containing generation related components in Gen AI applications.
A library for evaluating LLM-based applications.
Trustworthy memory for AI agents. The official OMEM Python SDK.
Trustworthy memory for AI agents. The official OMEM Python SDK.
Trustworthy memory for AI agents. The official OMEM Python SDK.
Trustworthy memory for AI agents. The official OMEM Python SDK.
Trustworthy memory for AI agents. The official OMEM Python SDK.
CLI and Python API to transcribe videos longer than 30 minutes with gemini-3.5-transcribe while mitigating free-tier 429 errors
Forgexa CLI — command-line client and AI agent runtime for the Forgexa platform
One window for an AI coding session on Windows or Linux: your agent hosted in a pty pane, with git, a file viewer and a shell beside it. Built on Claude Code; GitHub Copilot CLI is supported but not yet exercised.
Enterprise AI Database Copilot, Schema Graph Introspector & Autonomous Recovery Agent (CLI)
Open-source antivirus and runtime protection for AI agents, tools, MCP servers, plugins, skills, and package installs.
Reliability and audit-ready testing for LLM agents (Python bridge to the AgentEval engine).
An autonomous junior maintainer for GitHub repos, powered by Claude or OpenAI Codex — reviews PRs, triages issues, fixes CI
You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/...
Enterprise AI Database Copilot, Schema Graph Introspector & Autonomous Recovery Agent (CLI)
Official MCP server for the PuntersEdge Australian racing & sports odds API — live bookmaker odds, results and market movement for AI agents.
How AI agents understand codebases without wasting tokens — local-first, adapter-driven, progressive disclosure enforced by design
Model APIs (OpenAI, Anthropic, Google, xAI), open-weights releases (Llama, Mistral, Qwen), orchestration frameworks (LangChain, LlamaIndex, DSPy), vector DBs (Pinecone, Weaviate, pgvector), and evaluation tools.
Head to the Developers page for API access, or use our Prompt Generator to craft and test prompts against multiple models before you write a line of code.
Yes — every notable open-weights drop is covered with model card highlights, benchmark comparisons, and links to the Hugging Face repo.