Does it require a hosted service or paid API key?

The README describes it as local-first and lists no paid API key requirement.

Can it coordinate work between agents?

Yes. Signals support claim, lease extension, acknowledgment, expiration, and reclaim flows, but are not presented as a scheduler.

Can stored memories be changed or removed?

The server provides explicit deletion, review-only promotion, annotation, and revision that creates a successor with a supersession receipt.

What client transport does it use?

It uses local stdio MCP and can be launched by an MCP-compatible client.

Agent Memory Bridge

memorycoding-agentssqlitecoordinationlocal-first

Local MCP memory for coding agents, with governed records, retrieval, coordination signals, and recoverable run histories.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to Cursor Add to VS Code

Not yet automatically verified

We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag — we're steadily working through the catalog.

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Choose your client or environment

Target File:~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "zzhang82-agent-memory-bridge": {
      "command": "uvx",
      "args": [
        "agent-memory-bridge"
      ]
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Overview

Agent Memory Bridge stores shared engineering memory in local SQLite/WAL for use across coding agents and sessions. It supports explicit namespaces, lexical or optional local semantic retrieval, review-first changes, coordination signals, and durable run, event, and outcome records. Use it when you need inspectable cross-agent memory without a hosted service or opaque vector store.

Use cases

Share project decisions and gotchas across coding agents

Retrieve procedures, concepts, beliefs, and supporting records

Coordinate lightweight handoffs with claim, lease, and acknowledgment signals

Review and promote proposed learning into durable memory

Recover run state and evidence-bound outcomes after reconnects or compaction

Key features

Durable local memory backed by SQLite/WAL

FTS5 lexical retrieval with optional local embeddings

Review-first promotion, annotation, revision, and deletion workflows

Signal lifecycle with claims, leases, and acknowledgments

Receipt-bound feedback and evidence-context digests

Durable runs, structured events, recovery projections, and outcomes

Capabilities & Tool Schemas (17)Self-reported

Inspect callable tools, capabilities, and parameters exposed to AI agents by Agent Memory Bridge.

store

Callable MCP tool function

recall

Callable MCP tool function

browse

Callable MCP tool function

stats

Callable MCP tool function

forget

Callable MCP tool function

feedback

Callable MCP tool function

Documentation Overview

Agent Memory Bridge — governed project memory across sessions and tools

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

Terminal

pip install agent-memory-bridge

Install once; connect each coding client separately. Installing the package does not register AMB with every coding agent. Each client you want to use must be configured to launch AMB as an MCP stdio server. Clients that should share memory need to use the same configured local AMB home.

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.

Current package/source version: 0.33.0.

Published releases: see GitHub Releases.

The first win happens inside the coding agent, in a fresh session. CLI Explore/Inspect and doctor/verify are later checks, not that win.

1. Install AMB

For the Quick Start, use a virtual environment so every coding client can point at one stable Python launcher. Replace <venv-python> with the Python executable inside .amb-venv for your operating system.

bash

python -m venv .amb-venv
<venv-python> -m pip install agent-memory-bridge==0.33.0

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

bash

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

2. Connect the coding client you actually use

Installation and client registration are separate. Preview the setup for one client first:

bash

<venv-python> -m agent_mem_bridge setup --client <client>

setup is read-only by default: it detects or inspects only bounded client configuration locations and shows the exact AMB fragment or action it recommends. Use a supported client name such as codex, claude-code, vscode, cursor, cline, opencode, or another client listed in Integrations. Codex is the reference workflow.

If the preview marks that client as eligible for safe automatic configuration, you can explicitly apply it after review:

bash

<venv-python> -m agent_mem_bridge setup --client <client> --apply

Some clients remain preview/manual because AMB will not guess or rewrite an unsafe configuration format or path. In that case, copy the rendered fragment or follow the client-specific Integration guide. Repeat this step for every coding client you want to connect. To share the same project memory across clients, keep them pointed at the same configured AGENT_MEMORY_BRIDGE_HOME, then reload each client after registration.

Connection is proven when the coding client itself lists AMB tools such as store and recall. doctor and verify do not prove that an external client loaded MCP config.

3. Initialize the project

bash

<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.

4. Teach one real project decision

In the connected coding agent, teach a decision you actually made. For example:

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

The connected agent uses AMB's public store tool to persist the explicit decision and reason. AMB does not infer a durable decision from the code or archive the whole conversation.

Another valid example is a stack choice, such as staying local-first instead of adding Redis. The win is the decision plus reason, not any one technology.

5. Close the session, then ask again in a fresh one

End the first agent session completely. Open a new session against the same project, same client registration, and same AMB home. Ask a generic question:

What is required before we merge a pull request?

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

Exact Codex observation steps live 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.

Optional review, refresh, and troubleshooting

Human-first Explore answers “What does AMB currently know about this project?” Inspect answers “Why did this information surface for this question?” Both are local and read-only.

bash

<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?"

This is a conceptual view, not verbatim CLI output:

text

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

Code tells AMB WHAT the project is.

Conversations teach AMB WHY it is that way.

That distinction is a trust boundary: derived facts can be rebuilt from current code, while durable project knowledge remains explicit, reviewable, and governed.

Repository WHAT comes from a clean Git commit. If HEAD changes or the worktree is dirty, AMB will not present an old snapshot as current truth. Refresh is not automatic. Rerun the explicit primitive:

bash

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

Refreshing repository WHAT leaves durable project WHY unchanged. Explore is CLI-only, not MCP tool #18, and it does not rank context for the model.

first-run remains optional guided help; it is not the first-win path:

bash

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

Use health checks only when setup is uncertain. They do not prove that a coding client loaded MCP config:

bash

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

Integrations

AMB works through local stdio MCP. Generic MCP clients are supported; Codex is the reference workflow; Claude Code, Claude Desktop, Cursor, and Cline are documented; and Antigravity, OpenCode, and Hermes have locally tested configuration paths.

Integration labels are deliberately narrow and do not imply client certification. See Integrations for current setup instructions and boundaries.

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:

Memory concern	AMB approach
Current repository truth	Derived from a clean repository state and refreshed explicitly
Human decisions and constraints	Stored explicitly as governed durable memory
Changed knowledge	Revised or superseded instead of silently overwritten
Why context surfaced	Inspectable through local derived views and evidence paths
Cross-session reuse	Shared through the same configured local AMB home
Privacy	Local-first; no hosted memory service is required

Read the full README →View source on GitHub →

Related MCP Servers

View all in Knowledge & Memory View all alternatives

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars

Stargazers on the source repository.

Last commit

5d ago

Most recent push to the default branch.

Tools exposed

Callable tools this server registers over MCP.

Directory activity

1 views

Config copies, upvotes, and views on AllMCPs.

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Agent Memory Bridge

SQLite/WAL is the durable authority. FTS5 and optional local embeddings are derived indexes.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Agent Memory Bridge AllMCPs Directory Badge

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/zzhang82-agent-memory-bridge?style=directory)](https://allmcps.com/mcp/zzhang82-agent-memory-bridge)

HTML Embed

<a href="https://allmcps.com/mcp/zzhang82-agent-memory-bridge"><img src="https://allmcps.com/api/badge/zzhang82-agent-memory-bridge?style=directory" alt="Agent Memory Bridge on AllMCPs" /></a>

Technical Specs & Signals

CategoryKnowledge & Memory

PricingFree

4/5 checks healthy over the last 31d

57Quality signal: Good · 57/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20

Documentation & tools28/30

Adoption & activity5/15

Community engagement0/10

A guidance signal from public completeness & health data — not a user rating. New listings start lower and rise as they add docs, get verified, and grow adoption. Signals we can't observe for a listing are skipped, not counted against it.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 25d ago via OSV.dev · agent-memory-bridge (PyPI)

★ Featured

AllMCPs Server

The official MCP server for AllMCPs.com - submit and manage tools directly from your AI. The open directory for MCP servers. Connect Claude, Cursor, Windsurf, and AI agents to databases, tools, files, and APIs. Explore 10,000+ servers. AllMCPs is the premier, open directory for discovering, evaluating, and installing Model Context Protocol (MCP) servers to equip AI agents and LLMs with real-world superpowers.

Explore Server →

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to unlock edit access and the Official badge — proof is checked automatically, then reviewed by our team.

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 🧠 Knowledge & Memory →Best MCP servers for Memory & Knowledge →Alternatives to Agent Memory Bridge →Install in Claude Desktop Install in Cursor Install in VS Code

Agent Memory Bridge

memorycoding-agentssqlitecoordinationlocal-first

Local MCP memory for coding agents, with governed records, retrieval, coordination signals, and recoverable run histories.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to Cursor Add to VS Code

Not yet automatically verified

We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag — we're steadily working through the catalog.

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Choose your client or environment

Target File:~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "zzhang82-agent-memory-bridge": {
      "command": "uvx",
      "args": [
        "agent-memory-bridge"
      ]
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Overview

Use cases

Share project decisions and gotchas across coding agents

Retrieve procedures, concepts, beliefs, and supporting records

Coordinate lightweight handoffs with claim, lease, and acknowledgment signals

Review and promote proposed learning into durable memory

Recover run state and evidence-bound outcomes after reconnects or compaction

Key features

Durable local memory backed by SQLite/WAL

FTS5 lexical retrieval with optional local embeddings

Review-first promotion, annotation, revision, and deletion workflows

Signal lifecycle with claims, leases, and acknowledgments

Receipt-bound feedback and evidence-context digests

Durable runs, structured events, recovery projections, and outcomes

Capabilities & Tool Schemas (17)Self-reported

Inspect callable tools, capabilities, and parameters exposed to AI agents by Agent Memory Bridge.

store

Callable MCP tool function

recall

Callable MCP tool function

browse

Callable MCP tool function

stats

Callable MCP tool function

forget

Callable MCP tool function

feedback

Callable MCP tool function

Documentation Overview

Agent Memory Bridge — governed project memory across sessions and tools

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

Terminal

pip install agent-memory-bridge

Your project should not start over with every session

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.

Current package/source version: 0.33.0.

Published releases: see GitHub Releases.

The first win happens inside the coding agent, in a fresh session. CLI Explore/Inspect and doctor/verify are later checks, not that win.

1. Install AMB

bash

python -m venv .amb-venv
<venv-python> -m pip install agent-memory-bridge==0.33.0

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

bash

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

2. Connect the coding client you actually use

Installation and client registration are separate. Preview the setup for one client first:

bash

<venv-python> -m agent_mem_bridge setup --client <client>

If the preview marks that client as eligible for safe automatic configuration, you can explicitly apply it after review:

bash

<venv-python> -m agent_mem_bridge setup --client <client> --apply

Connection is proven when the coding client itself lists AMB tools such as store and recall. doctor and verify do not prove that an external client loaded MCP config.

3. Initialize the project

bash

<venv-python> -m agent_mem_bridge project init .

4. Teach one real project decision

In the connected coding agent, teach a decision you actually made. For example:

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

The connected agent uses AMB's public store tool to persist the explicit decision and reason. AMB does not infer a durable decision from the code or archive the whole conversation.

Another valid example is a stack choice, such as staying local-first instead of adding Redis. The win is the decision plus reason, not any one technology.

5. Close the session, then ask again in a fresh one

End the first agent session completely. Open a new session against the same project, same client registration, and same AMB home. Ask a generic question:

What is required before we merge a pull request?

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

Exact Codex observation steps live 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.

Optional review, refresh, and troubleshooting

Human-first Explore answers “What does AMB currently know about this project?” Inspect answers “Why did this information surface for this question?” Both are local and read-only.

bash

<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?"

This is a conceptual view, not verbatim CLI output:

text

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

Code tells AMB WHAT the project is.

Conversations teach AMB WHY it is that way.

That distinction is a trust boundary: derived facts can be rebuilt from current code, while durable project knowledge remains explicit, reviewable, and governed.

Repository WHAT comes from a clean Git commit. If HEAD changes or the worktree is dirty, AMB will not present an old snapshot as current truth. Refresh is not automatic. Rerun the explicit primitive:

bash

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

Refreshing repository WHAT leaves durable project WHY unchanged. Explore is CLI-only, not MCP tool #18, and it does not rank context for the model.

first-run remains optional guided help; it is not the first-win path:

bash

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

Use health checks only when setup is uncertain. They do not prove that a coding client loaded MCP config:

bash

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

Integrations

Integration labels are deliberately narrow and do not imply client certification. See Integrations for current setup instructions and boundaries.

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:

Memory concern	AMB approach
Current repository truth	Derived from a clean repository state and refreshed explicitly
Human decisions and constraints	Stored explicitly as governed durable memory
Changed knowledge	Revised or superseded instead of silently overwritten
Why context surfaced	Inspectable through local derived views and evidence paths
Cross-session reuse	Shared through the same configured local AMB home
Privacy	Local-first; no hosted memory service is required

Read the full README →View source on GitHub →

Related MCP Servers

View all in Knowledge & Memory View all alternatives

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars

Stargazers on the source repository.

Last commit

5d ago

Most recent push to the default branch.

Tools exposed

Callable tools this server registers over MCP.

Directory activity

1 views

Config copies, upvotes, and views on AllMCPs.

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Agent Memory Bridge

SQLite/WAL is the durable authority. FTS5 and optional local embeddings are derived indexes.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/zzhang82-agent-memory-bridge?style=directory)](https://allmcps.com/mcp/zzhang82-agent-memory-bridge)

HTML Embed

<a href="https://allmcps.com/mcp/zzhang82-agent-memory-bridge"><img src="https://allmcps.com/api/badge/zzhang82-agent-memory-bridge?style=directory" alt="Agent Memory Bridge on AllMCPs" /></a>

Technical Specs & Signals

CategoryKnowledge & Memory

PricingFree

4/5 checks healthy over the last 31d

57Quality signal: Good · 57/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership10/20

Documentation & tools28/30

Adoption & activity5/15

Community engagement0/10

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 25d ago via OSV.dev · agent-memory-bridge (PyPI)

★ Featured

AllMCPs Server

Explore Server →

Own this project?

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 🧠 Knowledge & Memory →Best MCP servers for Memory & Knowledge →Alternatives to Agent Memory Bridge →Install in Claude Desktop Install in Cursor Install in VS Code