Know a great AI tool or AI news source? Submit it to AiByts
AiByts
Sign inGet started

tool calling

255 stories

Stories

← Back to the latest stories

  • Under the Hood: Serving Kimi K3

    How DigitalOcean served Kimi K3 on day 0: GPU selection (B300/MI350X), vLLM tuning, and the OpenAI-compatibility fixes for tool calling, streaming, and reasoning.

    DigitalOcean Blog14 min read

  • Designing Agent-Ready APIs

    AI agents are becoming API consumers. What that changes about API design, from descriptions as prompts and actionable errors to MCP as the new surface.

    Routebase Blog5 min read

  • From Fixed Agent Workflows to Intelligent Communication

    Fixed agent workflows break when reality diverges from the happy path. Mozaik replaces predefined graphs with an event-driven runtime — and agents that decide when and with whom to communicate through tool calling.

    Mozaik Blog3 min read

  • Using Local Coding Agents

    Using Open-Weight Models in Local Coding Harnesses as an Alternative to Claude Code and Codex Subscriptions

    Sebastian Raschka29 min read

  • Extending the Cline loop with plugins and hooks

    Learn how to extend the Cline agent loop with plugins and hooks to add custom behavior, lifecycle logging, and enforceable guardrails without rebuilding the harness.

    Cline9 min read

  • Prompt chaining explained: how to build reasoning pipelines in Python

    Last Updated on June 12, 2026 Imagine asking a friend who has never baked anything to produce a multi-layered cake. No recipe. No step-by-step instructions. Just: “Make me a three-tier cake with buttercream frosting and a fruit filling.” The result would be unpredictable at best.

    Sebastian Thrun’s Introduction To Machine Learning Blog19 min read

  • LangChain agents tutorial: build a multi-step workflow in Python

    Last Updated on June 12, 2026 A chatbot that answers questions from a knowledge base sounds impressive in a demo. Then someone asks it a question that requires checking two sources, comparing the results, and deciding whether to follow up.

    Sebastian Thrun’s Introduction To Machine Learning Blog21 min read

  • Agentic AI architecture: how to design multi-agent systems that actually work

    Last Updated on June 12, 2026 Picture a support operations pipeline built to handle billing inquiries. A customer writes in with a request that combines a billing dispute, a policy exception they read about on a forum, and an account that is missing three months of usage data because of a migration…

    Sebastian Thrun’s Introduction To Machine Learning Blog20 min read

  • How AI Agents Use Tools (Function Calling explained)

    Most people think LLMs are just for chatting, but tool calling turns them into agents that can actually do work. Function calling is the "bridge" that allows AI agents in Generative AI to move beyond simple chat and actually perform actions in the real world.

    The One AI Architect

  • Improved performance and model support with GGUF

    Ollama 0.30 is now available with improved performance and GGUF model compatibility through llama.cpp. This augments Ollama's MLX engine on Apple silicon, bringing support to more models on a wider range of hardware.

    Ollama Blog2 min read

  • Why the AI Policy Debate Should Focus More on the Harness and Protocol Layers

    Raffi Krikorian, the chief technology officer of Mozilla, has spent the past few months building an argument that the central question in AI isn't open versus closed, but owning versus renting—whether AI becomes something we control or something we lease from a handful of companies.

    Tech Policy Press37 min read

Showing 198 of 255 stories

Load more stories
AiByts Weekly Brief

Get the top AI news and tools straight to your inbox every week.

Weekly · AI news

Join 15,000+ AI enthusiasts