Back to Ecosystem Pulse
ToolProduction Ready
claude_codex_bridge
by bfly123
Real-time bridge for Claude, Codex, and Gemini with persistent context
Python
Updated Jul 26, 2026
Share:
Summary
Enables real-time collaboration between Claude, Codex, and Gemini with shared persistent context to reduce token usage. Routes messages and maintains per-agent context stores so multiple LLMs can work together without repeating state. Includes a cross-platform CLI and lightweight Python SDK for low-latency multi-agent workflows. real-time collaboration and shared persistent context help streamline multi-vendor coordination.
Why It Matters
As agents coordinate more complex workflows, keeping a consistent shared context while minimizing token overhead becomes essential for reliability and cost control. This bridge makes it practical to combine different LLM strengths in a single session, which helps surface agent interaction patterns and failure modes that matter for trust. By making multi-vendor collaboration repeatable, it supports reproducible agent-to-agent evaluation and tracking of agent behavior over time. This is particularly valuable for teams aiming to enable multi-vendor collaboration across models.
Ideal For
Teams building multi-vendor agent workflows who need low-latency, context-persistent collaboration across different LLM providers. This fits well for those seeking low-latency across models and providers.
Applications
- Coordinating specialist agents (code, reasoning, search) in a single session while preserving shared state
- Reducing token costs by maintaining persistent per-agent context across interactions
- Rapid prototyping of multi-LLM pipelines that combine Claude, Codex, and Gemini
- Logging agent interactions for later agent-to-agent evaluation and debugging
Works With
openaianthropicgooglepython
Topics
ai-collaborationai-toolsclaude-codeclicodexcross-platformgeminillmmulti-agent-systemspython+1 more
Similar Tools
autogencrewai
Keywords
multi-agent orchestrationmulti-agent trustagent delegationpython