chitta-bridge

Chitta Bridge

MCP server for multi-model AI discussions — works with Claude Code and Codex CLI. Connect to any AI backend: cloud agentic CLIs and local GPU models.

Quick Start

uv pip install git+https://github.com/genomewalker/chitta-bridge.git

chitta-bridge-install               # both Claude Code + Codex
chitta-bridge-install claude-code   # Claude Code only
chitta-bridge-install codex         # Codex CLI only

Skills (Codex): /review, /rescue, /room, /soul — plus all mcp__chitta_bridge__* tools.

Features

• Multiple backends: Codex CLI and local GPU models (Ollama/vLLM)
• Continuous sessions: Conversation history persists across messages
• Session warmup: background ping captures session ID — subsequent calls skip cold start
• Agentic execution: Full-auto mode with sandboxed file operations (Codex)
• Variant control: Set reasoning effort (minimal to max)
• File/image attachment: Share code files and images for context
• Discussion rooms: async multi-agent roundtables — any mix of backends respond in parallel, see the full thread, synthesize into one answer

Installation

With uv (recommended)

uv pip install git+https://github.com/genomewalker/chitta-bridge.git

With pip

pip install git+https://github.com/genomewalker/chitta-bridge.git

From source

git clone https://github.com/genomewalker/chitta-bridge.git
cd chitta-bridge
pip install -e .

Register

chitta-bridge-install               # install for both Claude Code and Codex
chitta-bridge-install claude-code   # Claude Code only (registers MCP server)
chitta-bridge-install codex         # Codex CLI only (plugin + skills + MCP)
chitta-bridge-uninstall             # uninstall from both
chitta-bridge-uninstall codex       # uninstall from Codex only

Verify: claude mcp list (Claude Code) or check ~/.codex/plugins/ (Codex)

Shared With cc-soul

When cc-soul is installed on the same machine, chitta-bridge should be treated as a frontend adapter, not a separate memory stack:

• cc-soul owns the shared backend: chittad, chitta, chitta-mcp, and ~/.claude/mind
• chitta-bridge adds Codex- and MCP-facing tools on top of that backend
• updating chitta-bridge changes frontend glue, not the shared daemon or memory store

For a dual-frontend setup, install the shared backend first, then add adapters:

cd cc-soul
./scripts/shared-stack.sh install all

Discussion Rooms

Async multi-agent roundtable with agent souls — participants get persistent identity, memory, tools, and structured challenge rounds.

Basic Room

room_create(
    room_id="my-room",
    topic="What's the best way to design a cache invalidation strategy?",
    participants='[
        {"name":"Codex","backend":"codex","session_id":"codex-1"},
        {"name":"Llama","backend":"local","model":"qwen2.5:32b","base_url":"http://gpunode:11434/v1"}
    ]'
)

room_run(room_id="my-room", rounds=2)
room_synthesize(room_id="my-room")

Soul-Powered Room

Each participant can have a soul — a system prompt, memory namespace, tools, challenge bias, and response format:

room_create(
    room_id="expert-panel",
    topic="How should we authenticate ancient DNA from permafrost?",
    participants='[
        {"name":"Paleogenomicist","backend":"local","model":"qwen2.5:32b",
         "base_url":"http://gpunode:11434/v1",
         "soul":{
           "system_prompt":"You are a senior paleogenomicist with 15+ years experience...",
           "realm":"agent:paleogenomicist",
           "tools":["recall","remember","web_search","smart_context"],
           "max_tool_turns":2,
           "challenge_bias":0.7,
           "response_format":"### Key Points\\n### Tools & Thresholds\\n### Caveats"
         }},
        {"name":"Bioinformatician","backend":"local","model":"phi4:14b",
         "base_url":"http://gpunode:11434/v1",
         "soul":{
           "system_prompt":"You are a computational biologist specializing in pipelines...",
           "realm":"agent:bioinformatician",
           "tools":["recall","remember","smart_context"],
           "challenge_bias":0.4
         }}
    ]'
)

# Challenge mode: between rounds, a moderator extracts claims and
# forces participants to disagree, provide evidence, and refine
room_run(room_id="expert-panel", rounds=2, challenge=true)
room_synthesize(room_id="expert-panel")

Soul Features

Feature	Description
system_prompt	Agent identity, expertise, personality
realm	Chitta memory namespace — per-agent persistent memory
tools	Available tools (see Agent Tools below)
max_tool_turns	Max tool-use iterations per response (default 3)
max_rounds	Max discussion rounds, 0 = unlimited
challenge_bias	0 = agreeable, 1 = devil's advocate
response_format	Structured output template