S40911120
Featured
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 repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It introduces a multi-agent orchestration system that routes tasks to different OpenAI models based on cost and effort, while maintaining strict isolation so native Claude remains unchanged.
Who it is for
- Developers who want to automate complex software tasks with AI agents
- Teams using Claude Code and seeking cost-aware model routing
- Power users who need reproducible, approval-gated AI workflows
- Researchers exploring multi-agent orchestration patterns
Use cases
- Automated code reviews and security analysis using dedicated verifier agents
- Low-cost exploration and broad search before committing expensive model calls
- Interactive coding sessions with balanced model routing for prototyping
- Running Claude Code with a controlled, auditable agent policy for sensitive repositories
Strengths
- Session isolation ensures native Claude Code is never altered and no files are written to ~/.claude
- Cost-aware agent fleet reduces expenses by using cheaper models for exploration and mechanical tasks
- Approval-gated installation with SHA-256 verification and GitHub attestation
- Extensive documentation with architecture, gateway runbook, and security policy
Considerations
- Requires a compatible Anthropic Messages gateway; not a standalone proxy
- Does not support native Claude Code connectors when running remora
- Not tested on WSL; gateway cooldown issues can cause retry storms if mishandled
README quick start
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
Description
Session-scoped GPT-5.6 agent routing for Claude Code
Related repositories
Similar projects matched by category, topics, and programming language.
7-e1even
Featured
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
Featured
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.