coding agents: 127 curated resources
coding agents
127 resources · page 4 of 4
Best practices for using GitHub Copilot to work on tasks
by GitHub
GitHub documentation on scoping issues and repository instructions to get good results from the Copilot cloud coding agent.
IBM Granite agent cookbook
IBM Granite agent cookbook GitHub repo: notebooks on building agents with Granite models.
IBM Granite legal cookbook
IBM Granite legal cookbook GitHub repo: notebooks applying Granite models to legal research and analysis.
NPI: How to ensure your agent is ready every time you ship (Intercom)
by Intercom
Intercom post on the product-introduction process that checks its Fin agent is ready for each product launch.
Context Engineering for Agents (LangChain Blog)
by LangChain
LangChain post on context engineering for agents: write, select, compress and isolate strategies.
Llama Cookbook
by Meta Llama
Meta Llama Cookbook GitHub repo: recipes for Llama inference, fine-tuning, RAG and integrations.
Mistral Cookbook
by Mistral AI
Mistral Cookbook GitHub repo: example notebooks for Mistral models and services from staff, community and partners.
OpenAI Agents SDK guide
by OpenAI
OpenAI Agents SDK guide explaining how the SDK's agents, tools, handoffs and tracing fit together.
Build skills (ChatGPT Learn)
by OpenAI
OpenAI documentation on building skills that add capabilities to ChatGPT and Codex, following the Agent Skills format.
OpenAI Cookbook (developers.openai.com)
by OpenAI
OpenAI Cookbook on the developer site: runnable examples for APIs, agents, evaluation and multimodal workflows.
Paperclip docs: Handling approvals
by Paperclip
Paperclip developer guide on handling human approvals for autonomous agents.
Phi Cookbook
by Microsoft
Microsoft Phi Cookbook GitHub repo: guides for deploying, fine-tuning and building apps with Phi small language models.
PolicyEngine: AI explanations grounded in tax-benefit calculations
by PolicyEngine
PolicyEngine post on an AI feature that explains household tax and benefit results computed by its rules engine.
Qwen-Agent docs
by Qwen
Qwen-Agent documentation: open-source agent framework for Qwen models with tool integration and examples.
Remotion agent skills
by Remotion
Remotion skills GitHub repo: agent skills for creating videos programmatically with Remotion.
Roo Code docs: Boomerang tasks
by Roomote
Roo Code documentation on Boomerang tasks: an orchestrator mode that delegates subtasks to specialised modes.
Refreshed Agentforce Guide (Salesforce)
by Salesforce
Salesforce post on its refreshed Agentforce guide to context engineering, instruction writing and Agent Script.
开源大模型食用指南 / Self-LLM
by Datawhale
Datawhale Self-LLM GitHub repo: Chinese tutorials for deploying and fine-tuning (full and LoRA) open models on Linux.
Writing effective tools for AI agents: using AI agents (Anthropic)
by Anthropic
Anthropic post on writing tools for agents and using agents to evaluate and improve those tools.
Z.ai developer documentation
Z.ai quick-start guide: API setup for GLM models, the GLM Coding Plan and Python and Java SDKs.
A harness for every task: dynamic workflows in Claude Code
by Anthropic
Claude blog post on dynamic workflows in Claude Code, where it writes and orchestrates its own multi-agent harness.
Code Mode: the better way to use MCP (Cloudflare Blog)
by Cloudflare
Cloudflare post on Code Mode, where agents write TypeScript against MCP APIs instead of calling tools directly.
Effective harnesses for long-running agents
by Anthropic
Anthropic post on harnesses for agents that work across many sessions, using an initializer agent and incremental progress.
FINOS AI Governance Framework
by FINOS
FINOS AI Governance Framework: open-source controls for adopting AI in financial services, mapped to risks.
Harness design for long-running application development
by Anthropic
Anthropic post on harness design for agents that build applications over long runs.
NAVER D2
by NAVER
NAVER D2 Hello World: Korean engineering blog from NAVER developers.
OpenAI API Skills guide
by OpenAI
OpenAI API skills guide: creating reusable skills for Responses API shell tools and Agents API sandboxes.
Building production-ready agentic systems: Lessons from Shopify Sidekick
by Shopify
Shopify Engineering post on lessons from building the Sidekick agent: architecture, LLM judges calibrated to human labels and RL pitfalls.
How we made v0 an effective coding agent (Vercel)
by Vercel
Vercel engineering post on v0's coding-agent pipeline: dynamic system prompts, streaming fixes and autofixers.
EASA AI Concept Paper Issue 2
by European Union Aviation Safety Agency (EASA)
EASA AI Concept Paper Issue 2: guidance on assuring Level 1 and 2 machine-learning applications in aviation.
Context Engineering for AI Agents: Lessons from Building Manus
by Manus
Manus post on context engineering lessons: designing around the KV cache, masking tools and using the filesystem as memory.