S40911120
精选
recensa
Recensa is a self-hosted web viewer that indexes Claude Code session transcripts into a local SQLite database, enabling full-text search, replay, and audit of all past agent conversations without uploading data anywhere.
AI 仓库情报摘要
FR-AI / ANALYSIS为什么值得关注
它引入了一种多智能体编排系统，根据成本和努力程度将任务路由到不同的 OpenAI 模型，同时保持严格隔离，使原生 Claude 保持不变。
适合谁使用
- 希望用 AI 智能体自动化复杂软件开发任务的开发者
- 使用 Claude Code 并需要成本感知模型路由的团队
- 需要可重现、经审批的 AI 工作流的高级用户
- 探索多智能体编排模式的研究人员
典型使用场景
- 使用专用验证智能体进行自动化代码审查和安全分析
- 在调用高成本模型之前进行低成本探索和广泛搜索
- 使用平衡模型路由进行交互式编码，快速制作原型
- 对敏感仓库使用受控、可审计的智能体策略运行 Claude Code
项目优势
- 会话隔离确保原生 Claude Code 不会被修改，且不会写入 ~/.claude 文件
- 成本感知的智能体舰队通过使用更便宜的模型进行探索和机械任务来降低开销
- 经审批的安装流程，包含 SHA-256 验证和 GitHub 证明
- 包含架构、网关运行手册和安全策略的详尽文档
使用前须知
- 需要兼容的 Anthropic Messages 网关；并非独立代理
- 运行 remora 时不支持原生 Claude Code 的连接器
- 未在 WSL 上测试；处理不当时网关冷却问题可能导致重试风暴
README 快速开始
remora
Run Claude Code with a cost-aware GPT-5.6 agent fleet for one session.
remora launches Claude Code with session-scoped OpenAI model routing, role agents, and orchestration. Sol handles planning and critical review, Luna handles lower-cost exploration and implementation, and Terra is the balanced interactive option. Exiting the child session removes every override.
Contents
- What remora changes
- Architecture and model map
- Requirements
- Install
- Configure
- Use
- Isolation and security
- Troubleshooting
- Uninstall
- Support remora
- Further reading
What remora changes
Core guarantee: plain
claudekeeps its original credentials, settings, agents, and model routing. remora changes only the child process it launches.
| Surface | Native claude | remora session |
|---|---|---|
| Command | Unchanged | Separate remora executable |
| Authentication | Existing Anthropic login | Child-only gateway token |
| Settings | Existing Claude hierarchy | Session routing and caller settings |
| Agents | Project/user/plugin agents | Eight session roles |
| Model fallback | Existing behavior | Automatic fallback disabled |
Files under ~/.claude | Unchanged | Never written |
| Runtime marker | Absent | REMORA_ACTIVE=1 in the child |
Large Plans use a reviewed program envelope followed by independently
approvable execution slices. Two automatic REVISE verdicts pause only the
affected readiness unit; unrelated READY slices may proceed after explicit
approval. By default, the next executable slice is reviewed and presented for
approval before downstream slices. Security-sensitive units require read-only
security evidence before the first Plan review for that unit. The complete contract belongs in
the architecture document.
Architecture and model map
flowchart LR
USER["Developer"] -->|claude| NATIVE["Native Claude Code"]
USER -->|remora| LAUNCHER["remora launcher"]
LAUNCHER -->|child-only environment| GATEWAY["Anthropic-compatible gateway"]
LAUNCHER -->|session agents and policy| RUNTIME["Claude Code runtime"]
RUNTIME
项目描述
Session-scoped GPT-5.6 agent routing for Claude Code
相关仓库与替代方案
根据分类、Topic 和编程语言匹配的相似项目。
7-e1even
精选
learn-agent
A collection of notes on building coding agents, derived from the production development of the desktop agent Reina, with each mechanism simplified into a zero-dependency, single-file Node.js demo.
makecindy
精选
cindy
Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.