Building Agents

Build A2A servers and clients so agents from different frameworks can talk

List, create, update and revoke AltLLM Portal API keys from the local CLI

Navigate the AltLLM Portal CLI across auth, API keys, billing and payment links

Use NEAR AI Cloud for private, verifiable inference with signed chat messages

Build and deploy autonomous agents with the OpenServ SDK and its client package

Manage OpenServ agents, workflows, triggers and tasks through the Platform client

Build AI agents that act on Solana with 60+ actions, LangChain and MCP setup

Scaffold a Harbor benchmark adapter and guide its implementation from the spec

Scaffold a Harbor evaluation task with instructions, environment and verifier

Compile files and folders into Harbor tasks and run map-reduce eval jobs

Publish Harbor tasks and benchmark datasets to the Harbor registry

Write Reward Kit verifiers with LLM judges that score task output

Design n8n AI agents with tool calling, memory and system prompts

Work on a LangChain or LangGraph agent project scaffolded by agents-cli

Write Google ADK agent code with tools, callbacks, state and agent types

Run and analyze evaluations for ADK agents with eval datasets and failure review

Set up tracing, logging and monitoring for deployed ADK agents on Google Cloud

Publish ADK agents to Gemini Enterprise and manage them in the Agent Registry

Scaffold new agent projects with CI/CD and deployment setup using agents-cli

Follow the ADK agent lifecycle from local runs and debugging to deployment

Build reactive multi-agent systems in Java with AgentScope and Project Reactor

Route AI, LLM, agent, RAG and prompt questions to the right guides

Design, build, debug and upgrade GitHub agentic workflows with the right prompts

Create VS Code custom agent files with tools, instructions and handoffs

Run one-shot Gemini CLI prompts for questions, summaries and generated text

Call local AI models through the AIGCPanel CLI or HTTP API and batch process media

Build durable backend AI agents with tools, skills, schedules and evals

Add chat, summaries, embeddings and transcription with the Workers AI binding

Call LLMs from code snippets, compare models and run batch inference

Design and evaluate agentic harnesses with tool use, permissions and approval gates

Design and evaluate agentic harnesses for LLM tools with approvals and memory

Design and evaluate agentic harnesses for developer tools and copilots

Score options on weighted dimensions and output a ranked TSV

Scaffold an Oracle AI Database agent with NL2SQL, RAG, Grok 4 and Open WebUI

Scaffold a small RAG chatbot on Oracle 26ai Free with LangChain and Open WebUI

Scaffold a tool-calling agent over an Oracle schema with LangChain and in-db embeddings

Write Gemini API code for text, chat, images, video, speech and tools

Build real-time audio and video streaming apps with the Gemini Live API

Compare model costs for a task and find the cheapest adequate option

Run open model inference and fine-tuning on Fireworks with a chat API

Call the Groq LPU inference API for chat, vision, speech and tool calling

Evaluate LLM outputs with judge models, rubrics and pairwise comparisons

Run serverless inference, embeddings and fine-tuning on 200+ open models

Build and debug OpenRouter API integrations with routing, tools and output

Build LLM and multi-agent apps with LazyLLM workflows and fine-tuning

Run a streaming chat assistant that keeps memory across multi-turn conversations

Give brief, focused answers from a general-purpose JetBrains Koog assistant

Score agent responses from 0 to 10 for helpfulness, accuracy and clarity

Run one AI assistant across web chat, Telegram, Slack, Discord and WhatsApp