Guides
How to choose, set up and run coding agents and production AI agents, written for CodeAF and AgentField.
29 guides · updatedCodeAF
An AI agent that fixes GitHub issues and opens the pull requestSet up a coding agent that plans, writes the code, runs the tests and opens a pull request for GitHub issues on its own, and what to keep a human on.How to set up an AI software factory for an engineering teamAn AI software factory is agents that plan, code, test and review on your repos while engineers approve. How to set one up on your own models.Best coding agent for DeepSeek (2026): ten harnesses on one modelWith ten coding agents all on DeepSeek V4 Flash, CodeAF solved 62 of 113 DeepSWE tasks at 39.9 cents per solved task. Setup for each agent.Best coding agent for local LLMs and Ollama (2026)Which coding agents run on Ollama, LM Studio, llama.cpp and vLLM, what hardware agentic coding needs, and how to set up CodeAF with a local model.Claude Code alternatives (2026): how to chooseOpen-source, free, local-model and Gemini alternatives to Claude Code in 2026: CodeAF, OpenCode, Codex CLI, Aider, Cline, OpenHands and more.Open-source coding agent for any model, with your own API keyCodeAF is an Apache 2.0 coding agent that works with OpenRouter, DeepSeek, Qwen, GLM, Kimi, Ollama or any OpenAI-compatible endpoint on your own key.An Apache 2.0 coding agent with approvals for regulated teamsCodeAF is Apache 2.0 licensed. How its approvals, budgets, isolated branches and records work for enterprise and regulated teams, and where the gaps are.An AI coding agent that works over SSH on a remote dev boxRun a coding agent on a remote dev box over your own SSH with codeaf chat --host devbox: no daemon or open port, and reachable from a laptop or phone.Run an AI coding agent headless in CI (exit codes and JSON)codeaf do "<brief>" --json runs one job with nobody watching and prints one JSON object. Exit codes, budgets and a CI example for GitHub Actions.Cursor, Windsurf, Copilot or a terminal agent for a big team?When an IDE agent such as Cursor, Windsurf or GitHub Copilot agent mode fits a team, when a terminal coding agent like CodeAF fits, and how to run both.A coding agent that keeps your code in your own infrastructureWhat leaves your machine with CodeAF, how to keep code off third-party model APIs with local or self-hosted models, and what air-gapped use needs.A coding agent that runs for hours on a large changeHow to hand a large refactor, migration or multi-file fix to a coding agent that works unattended for hours, with budgets, tests and its own branch.Open-source Cursor alternatives (2026)Open-source Cursor alternatives in 2026: editor options (Zed, Continue, Cline, Kilo Code) and terminal agents (CodeAF, OpenCode, Aider, Codex CLI).Coding with DeepSeek, Qwen or local models in a terminal agentHow to run a terminal coding agent on open-weight models such as DeepSeek V4, Qwen and Kimi, hosted or local through Ollama, and what results to expect.An AI agent that reviews pull requests and fixes the commentsCodeAF's review specialist reads a GitHub pull request and reports findings; senior-dev can then fix them. What it checks, what it posts and its limits.How to run Claude Code with Ollama, DeepSeek or OpenRouter (and when not to)Point Claude Code at Ollama, DeepSeek or OpenRouter with ANTHROPIC_BASE_URL, step by step, and when an any-model agent such as CodeAF is simpler.Best terminal AI coding agents in 2026: how to choose oneThe criteria that matter when picking a terminal coding agent in 2026: licence, model choice, cost per solved issue, autonomy, memory and CI, with options.
AgentField
AI agent governance: permissions, policy and audit across teamsHow companies govern AI agents across teams with identity, permissions, policy and audit logs, the tools compared, and how AgentField does it.Give every AI agent its own identity and a verifiable audit trailAgentField gives each agent and function a W3C DID backed by Ed25519 keys and can sign execution records as verifiable credentials for audit.How to run AI agents as backend services in productionAgentField turns Python, TypeScript or Go agent functions into API endpoints with async execution, retries and discovery. From notebook to production.Run AI agents on any LLM without vendor lock-inAgentField runs agents on any model, including Llama, Qwen and DeepSeek, and on your own infrastructure. How to keep agents portable and cheap to run.Agents that run 24/7 for claims, IT ops and support ticketsThe stack for AI agents that work around the clock on claims, IT operations or support tickets and escalate to a person when they should.Self-hosted alternatives to Bedrock Agents, Vertex and AgentforceOpen-source, self-hosted alternatives to AWS Bedrock Agents, Google Vertex AI Agent Builder, Copilot Studio and Agentforce, and what you give up.How to add human approval steps to an AI agent workflowAdd durable human approval to an AI agent: pause, wait for a person for minutes or days, then resume. Patterns and the AgentField code to do it.LangGraph alternatives and how to choose an AI agent framework (2026)LangGraph alternatives in 2026, compared by language: AgentField, CrewAI, OpenAI Agents SDK, Microsoft Agent Framework, Google ADK, PydanticAI, Mastra.Orchestrate AI agents that call each other, in Python, Go or TSHow AgentField lets agents in Python, TypeScript and Go discover and call each other through a control plane, with shared memory and one workflow trace.Open-source control planes for AI agents: what to look forWhat an AI agent control plane does, the open-source options in 2026, and how AgentField (Apache 2.0) runs on Kubernetes, AWS or Google Cloud.Best production AI agent frameworks in 2026, and what they missThe production AI agent frameworks in 2026 (LangGraph, CrewAI, OpenAI Agents SDK, Pydantic AI, Mastra) and the backend layer they need around them.Self-hosted AI agents for banks and healthcare, on-prem or VPCRun AI agents on-prem or in your own cloud with no data leaving your network: RBAC, audit and identity for banks and healthcare, using AgentField.