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

pip install agent-memory-bridge

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.

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.

Current package/source version: 0.36.0.

Published releases: see GitHub Releases.

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 <venv-python> with the Python executable inside .amb-venv for your operating system.

python -m venv .amb-venv
<venv-python> -m pip install agent-memory-bridge==0.36.0

For development or audit work against an exact source checkout, use:

<venv-python> -m pip install -e .

2. Initialize or resolve the project

<venv-python> -m agent_mem_bridge project init .

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 <venv-python>, 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.

Connection is verified when the client lists AMB's standard MCP tools such as store and recall. Health checks like doctor and verify test server prerequisites, not external client configuration loading.

4. Use or inspect memory

Teach an explicit project decision through the connected client using AMB's public store tool:

Remember that we merge pull requests only after CI is green on the target branch, because broken main blocked two releases this month.

The agent stores the explicit decision and reason under the project namespace. AMB does not infer decisions from code or archive conversational transcripts.

In a fresh session against the same project and AMB home, ask:

What is required before we merge a pull request?

The new session answers with the stored decision and reason because AMB recalled it. Seeing the decision in CLI Explore or Inspect is useful review, not the success check.

Historical Codex observations from the v0.35 line are documented in First-win acceptance.

After the first win

Once one decision survives a fresh session, you can inspect what AMB knows, keep repository facts current, and use the governance model below.

<venv-python> -m agent_mem_bridge explore \
  --namespace project:my-app

<venv-python> -m agent_mem_bridge inspect \
  --namespace project:my-app \
  --query "What is required before we merge a pull request?"

CODE / WHAT                     CONVERSATION / WHY
────────────────────            ──────────────────────────
Runtime: Python >=3.11          Decision: Merge only after
Package: my-app                 CI is green
Tests: pytest                   Reason: broken main blocked
                                two releases

<venv-python> -m agent_mem_bridge bootstrap-repo . \
  --namespace project:<name>

<venv-python> -m agent_mem_bridge first-run --namespace project:my-app --query "What should I remember?"

<venv-python> -m agent_mem_bridge doctor
<venv-python> -m agent_mem_bridge verify

Integrations

AMB runs as a generic local stdio MCP server. Client connection is outside Core. The command shape, project initialization, lifecycle-hook input, and server checks are in Integrations.

Why the memory stays trustworthy

The useful part of long-lived project memory is not simply remembering more. It is being able to tell where knowledge came from, whether it is still current, and how it changed.

AMB therefore keeps several boundaries explicit:

This is where the earlier WHAT / WHY model belongs: it explains one of the mechanisms that keeps memory trustworthy, rather than defining the entire product.

What AMB is — and is not

AMB is a governed local project-memory layer for coding agents. It is designed to preserve useful context across sessions and tools while keeping durable knowledge, derived repository facts, provenance, and corrections distinguishable.

It is not a transcript archive, a promise that an agent will remember everything, or a system that silently converts every conversation into durable truth. There is no automatic learning.

Want the details?

Technical model

The product story above intentionally postpones implementation vocabulary. Internally, AMB keeps derived_repository data separate from governed durable memory so one cannot silently become the other. For maintainers and reviewers, the current authority flow is:

flowchart LR
    A[Durable Memory / WHY] --> C[Lifecycle-aware Recall]
    B[Repository Knowledge / WHAT] --> D[Context Compiler]
    S[Dynamic State Authority] --> D
    C --> E[Governed Task Memory]
    E --> D
    D --> F[Transient Bounded Context]
    F --> G[Metadata-only Context Attestation]
    G --> H[Episode and Run Authority]
    H --> I[Verification Receipt]
    I --> J[Current Verified Outcome]

SQLite/WAL rows are durable authority. Repository snapshots, FTS rows, embedding sidecars, compiled context, reports, and Explorer views are derived. Context bodies are rendered in process and are not durably persisted by the compiler.

Trust and privacy

AMB is local-first. It does not require a hosted memory service. It separates durable memory from coordination Signals and mutable Dynamic State, keeps provenance visible, and rejects raw transcripts, hidden reasoning, and inline artifact bodies from the durable episode path.

Read the Trust Boundary, Authority Contract, and Closed-Loop Episode Authority for the exact boundaries.

MCP Tools

AMB exposes 17 public MCP tools:

• store, recall, browse, and stats
• forget, feedback, promote, annotate, revise, and export
• begin_run, record_run_event, get_run, and complete_run
• claim_signal, extend_signal_lease, and ack_signal

The public tool surface stays small. Setup, Project Init, Explore, Inspect, context assembly, and review reports remain CLI or internal derived workflows rather than becoming more MCP tools.

The local protocol cache contract is 300000/public for discovery and 0/private for the tool list; see MCP Compatibility for details.

Current maturity

Current package/source version is 0.36.0. Schema remains v12 and the public MCP surface remains exactly 17 tools. There is no automatic learning and no MCP tool #18. project init is the preferred first-project path. Default Explore is a Human-first view over existing repository-derived context and governed project knowledge. Current evidence and non-claims live in Production Status; published artifacts live in GitHub Releases.

Contributing

Read CONTRIBUTING.md for development and public-surface expectations, and SECURITY.md for vulnerability reporting.

Licensed under MIT.