Claude Code and OpenCode with local Qwen: compatible or supported?
OpenCode documents local llama.cpp. Claude Code can traverse a compatible gateway, but Anthropic does not support routing it to non-Claude models.
BLOGCategory
AI agents
Articles grouped by business problem, industry, and system type.
Codex with local Qwen3.8-27B over the Responses API
Codex can use a custom provider over the Responses wire. This guide shows the minimum profile, support boundary and the Qwen result.
How to benchmark a local coding agent honestly
A useful coding-agent benchmark needs work requests written like ordinary issues, clean workspaces, hidden checks, retained metrics and a separate review. This method evaluates a patch before acceptance.
Local Qwen Code: the medium profile from a home test
Wire-level reasoning effort, no fixed max_tokens, preserved thinking and task-scoped sessions removed observed failures in a home-PC experiment.
One Qwen, four clients: Qwen Code, Codex, Claude Code, OpenCode
Four clients drove the same local Qwen3.8-27B. We compare the tasks, elapsed time, hidden tests and actual code choices. OpenCode won one import; Qwen Code won the long run.
Qwen Code in practice: CSV, pagination and import
Four small tasks revealed more than one large benchmark. Qwen Code read contracts well at medium effort, but hidden tests still found a missing validation rule.
Qwen Code: 26 minutes to a frontend, 48 to acceptance
An empty folder, one sentence and local Qwen on a home RTX 3090. The first ATS dashboard took 26:03. Here are the prompt, output and complete repair cost.
Qwen3.8-27B on an RTX 3090: results, metrics and limits
A complete record of one home experiment with Qwen3.8-27B: serving profile, timings, tokens, energy, VRAM, coding tests, failures and limits.
How we isolated the local Qwen agent experiment
Clean fixtures, separate worktrees, hidden checks outside the agent folder, an explicit tool list, telemetry and retained diffs. We also name the gap: shell was not a full sandbox.
local llmqwen3.8securityexperiment
AI Agent vs Automation: Which Fits the Process?
Automation follows a defined path. An AI agent selects some later steps from case context. Compare control, exceptions, cost and maintenance before choosing.
AI App, AI Agent or Automation: How to Choose
An app gives people a working interface, automation follows a fixed process and an agent selects steps inside boundaries. Use this buyer router before scoping.
Personal AI agent vs ChatGPT vs Copilot: choose
ChatGPT is a general AI workspace, Microsoft 365 Copilot works across Microsoft 365 apps, and a personal agent is a configured process operator.
AI Training for Customer Service: Program and Price
A support workshop uses real ticket work to practise triage, reply drafts, source-linked answers and escalation. Closed team training starts from €1,200 net per day for a group of up to about 15 people.
Agent Migration: Reference Set and Return Path
Migrate an automation by capturing current behavior, reviewing each meaningful difference and exercising the return path before traffic moves.
AI Act Register: Put the Scope Gate Before the Model
An AI inventory should establish role, purpose and risk scope before a model drafts an explanation. This operational pattern keeps classification and review with accountable people.
Citations as Data in Case-Law Research
A legal-research system should show the exact source passage behind each proposition. Learn how to model citations, test retrieval and keep interpretation with a qualified lawyer.
Synthetic voice with a named release decision
A spoken reply carries the company's identity. This guide shows how to link source audio, extracted commitments and a named approval before speech synthesis runs.
Keep conflicting field evidence visible
Photos, voice notes and work cards can disagree. This guide shows how to preserve each source, model the conflict and record the human decision that closes a field case.
CrewAI or one agent: how to measure the choice
A crew earns its complexity when separate roles improve a defined workflow. Compare it with one agent on the same inputs, tools, rubric and operating cost before choosing the architecture.
Durable checkpoints for regulated document intake
A multi-day intake case should resume with its files, history and next action intact. This guide explains checkpoint design, replay safety and human approval for LangGraph workflows.