BerriAI/litellm-agent-platform
A simple, self-hosted infrastructure platform for running multiple agents in production.
SUMMARY AI要約 by gpt-5-mini
LiteLLM Agent Platform is a self‑hosted system for running coding agents (Claude Code, Codex, Hermes, etc.) inside isolated Kubernetes sandboxes with a credential vault so agents can operate with bypass permissions without seeing real keys. It’s used by developers and teams who need safe, reproducible agent execution for coding tasks and want local or cloud self‑hosting. Key features: - lap CLI, web UI and HTTP API to create agents, open sessions, and attach terminals over WebSocket - Per‑session Kubernetes pods (kubernetes-sigs/agent-sandbox) with stub creds swapped by a vault on outbound TLS - Supported harnesses: Claude Code, Codex, Hermes - Local dev via kind + Docker Compose; optional self‑hosted LiteLLM gateway proxy - Production deploy recommendations (AWS EKS, Render) - Developer API for programmatic control - MIT license, docs and demo included.
使用AIコーディングツール
このリポジトリには以下のAIコーディングツールの設定ファイルが置かれており、開発時にAIアシスタントが利用された痕跡があります。
DETECTED 検出されたAIスタック
このRepoのdescription / GitHub topics / READMEのAI要約に出現したAI関連キーワードをカテゴリ別に表示。各バッジは該当カテゴリの詳細ランキングへリンクします。
使用言語(バイト数比)
オーナー情報
日付
| GitHub作成日 | 2026-05-07 |
| 最終Push | 2026-05-10 |
| 当サイト初検出 | 2026-05-09 |
| 最終取得 | 2026-05-10 16:11 |
類似Repo (同じ言語のAI関連Repo)
Claude Code 桌宠伴侣 — 透明桌宠窗口实时显示 Claude Code 的工具调用、会话状态和完成提醒。
YieldDi/cc-devloopClaude Code Dev Loop
ArisRhiannon/vibecheckOffline, no-AI "safe to ship?" gate for vibe-coded apps — finds the security mistakes AI coding agents make (secrets, unprotected routes, eval-RCE, SQLi, CORS, JWT, leaked keys). CLI + MCP, agent-runnable.
neang-mengseang/LLM-RouterSelf-hosted OpenAI-compatible API that routes LLM requests across 14 providers with automatic failover.
civilization-os/CodeCartographerStatic code intelligence for generating architecture docs, call graphs, business flows, and structured repository maps with optional LLM-powered method understanding.
nithiin7/repo-chatA simple and powerful RAG chatbot that can index and intelligently answer questions about your codebase.
code-by-tiago/PlanifyPlataforma de Automação Educacional com IA Repositório oficial de uma aplicação web externa para o ecossistema Planify. O sistema utiliza modelos de linguagem (LLMs) para processar diretrizes pedagógicas, cronogramas estruturados de ensino automatizados e exportar materiais didáticos formatados (PDF/Docs) para educadores.
boggspa/TaskWraithLocal-first macOS workbench for running and reviewing AI coding agents — multi-provider, with multi-agent ensembles, diff review, and on-device history.