zzhang82/Agent-Memory-Bridge

Carry project decisions into the next coding session.
AMB helps coding agents remember the decisions that matter — across sessions, tools, and time.
简体中文
Connecting a specific coding client is outside AMB Core. AMB does not discover, write, or certify Codex, Claude, Cursor, OpenCode, Hermes, Cline, VS Code, or Antigravity. Clients configure AMB as a standard MCP stdio server independently, pointing to the same local AMB home when they share project memory. See Integrations for the generic installer and registration contract.
If an existing bridge lives at ~/.codex/mem-bridge, v0.36 does not open it automatically. Set AGENT_MEMORY_BRIDGE_HOME to that directory, or copy it to ~/.local/share/agent-memory-bridge. The configuration guide has the exact cutover.
Your project should not start over with every session
A project is more than its current files. Over time, useful context gets scattered across repositories, chats, coding agents, reviews, fixes, and one-off decisions. A new session can see the code but still miss the reasons that make the project make sense.
AMB gives those decisions a durable place to live. The first win is simple: teach one real decision, close the session, open a fresh coding-agent session, and hear the same decision come back from AMB.
| Without shared project memory | With AMB |
|---|---|
| Each session reconstructs context | Useful project knowledge carries forward |
| Decisions disappear into old chats | Explicit decisions and reasons stay with the project |
| Different tools build different partial pictures | Supported MCP clients can use the same configured local AMB home |
| Memory can become stale or ambiguous | Provenance, revision, supersession, and inspection keep it governable |
AMB is local-first and inspectable. It does not silently archive every conversation or treat every remembered statement as equal authority.
Quick Start
AMB requires **Python 3.11+**, Git, and an MCP-compatible coding client that can launch a local stdio server or connect via Streamable HTTP.
Current package/source version: 0.36.0.
Published releases: see GitHub Releases.
Agent setup (Recommended)
Install the official companion skills from Agent-Memory-Skills (amb for everyday memory and amb-connect for host capability discovery and connection):
- If you are in an agent CLI supporting skills (e.g. Claude Code, Cursor, OpenCode):
- Or read the skills directly:
- **amb** (Everyday memory recall, store, revise, annotate): SKILL.md (raw)
- **amb-connect** (Host capability discovery, stdio / Streamable HTTP MCP, tool profiles): SKILL.md (raw)
Copy Agent Prompt
Paste this into any coding agent chat to immediately configure and use AMB:
Manual Quickstart
The product story is four steps: install AMB, initialize or resolve a project, run the generic MCP server, and use or inspect memory. Client connection stays outside Core.
1. Install AMB
Use a virtual environment so the MCP server points at one stable Python launcher. Replace with the Python executable inside .amb-venv for your operating system.
For development or audit work against an exact source checkout, use:
2. Initialize or resolve the project
Project Init detects the local Git repository, proposes a namespace such as project:my-app, and waits for confirmation. It then derives a current repository baseline. It does not automatically learn decisions. Once bound, project resolve . can resolve the namespace for the checkout without reinitializing.
3. Run the generic MCP server
Run AMB as a standard MCP stdio server: command , arguments -m agent_mem_bridge, and a persistent AGENT_MEMORY_BRIDGE_HOME shared by any client accessing the project memory.
How a client launches that process is outside Core. The command shape is in Integrations.