AI / MLMédio

running-claude-code-via-litellm-copilot

porxixu-me·xixu-me· v1.0.0 · atualizado em 2026-04-10

Score

Use when routing Claude Code through a local LiteLLM proxy to GitHub Copilot, reducing direct Anthropic spend, configuring ANTHROPIC_BASE_URL or ANTHROPIC_MODEL overrides, or troubleshooting Copilot proxy setup failures such as model-not-found, no localhost traffic, or GitHub 401/403 auth errors.

claude-codelitellmgithub-copilotproxyanthropic-apillm-configuration

0Stars

0Forks

0Usos

Fork

Documento do Skill

SKILL.mdrunning-claude-code-via-litellm-copilot/workflow

Preflight Check: — Verify Claude CLI, uv/pip are working and user has Copilot access.

Setup Type: — Determine if temporary or persistent setup is needed.

Create `config.yaml`: — Configure LiteLLM with `model_name` and `github_copilot/<model>`.

Install LiteLLM: — Use `uv tool install "litellm[proxy]"` or `pip install "litellm[proxy]"`.

Start LiteLLM: — Run `litellm --config config.yaml --port 4000`.

Configure Claude Code: — Set environment variables or merge into `~/.claude/settings.json`.

Verification: — Test with a small prompt and check logs.

Telemetria de Agentes

Execuções

total

Taxa de Sucesso

últimos 30d

Latência Média

0.0s

p50

Alucinação

0.0%

detecção

Tokens Entrada

avg 0/exec

Tokens Saída

avg 0/exec

Uso por Plataforma

Skills Relacionados

Similar a ←AI SEO

60%

Similar a ←Using Skills

60%

Similar a ←Enhance Prompt for Stitch

60%

Árvore do Skill

running-claude-code-via-litellm-copilot

Fases Cognitivas6

1.SENSE

2.CONTEXTUALIZE

3.HYPOTHESIZE

4.RECOMMEND

5.ACT

6.EVALUATE

Triggers6

run Claude Code with GitHub Copilot via LiteLLMconfigure Claude Code to use a local LiteLLM proxyreduce Anthropic API spending with Claude Code and Copilottroubleshoot Claude Code and Copilot integration issuesset up ANTHROPIC_BASE_URL for Claude Code with Copilotuse LiteLLM to proxy Claude Code requests to GitHub Copilot

Avaliar este Skill

Score Breakdown

⭐Avaliação Humana0%

🤖Sucesso de Agentes0%

🕐Atualidade100%

🔗Saúde de Dependências100%

🕸️Centralidade no Grafo0%

🛡️Segurança50%

CompositeScore = α·Humano + β·Agente + γ·Recência + δ·Deps + ε·Centralidade + ζ·Segurança

Instalação

$ synaptic mcp download running-claude-code-via-litellm-copilot

$ synaptic skills detail running-claude-code-via-litellm-copilot

$ synaptic skills live running-claude-code-via-litellm-copilot

Dependências

litellm uv pip

Links

GitHub Repository