Lians Agent Memory

MCP文档知识

提供方 未标注

文档知识 stdio · 本地进程 未标注 社区 / 第三方 ClaudeCursorVS CodeGemini CLI
查看接入方式

双时态代理记忆,支持时间点检索、替代、审计追踪和受控记忆管理。

一句话选型结论

按资料字段整理

Lians Agent Memory 属于文档知识类 MCP 服务器,stdio · 本地进程,鉴权方式未标注,可直接接入 Claude、Cursor、VS Code 等,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类文档知识 传输方式stdio · 本地进程 鉴权未标注 部署方式本地部署
GitHub 星标 未标注 仓库热度,无公开仓库时显示未标注
工具数 未标注 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

文档知识
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量未标注暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

记忆

安装与配置

stdio · 本地进程 未标注
客户端在本机拉起子进程,数据不出本机
codex mcp add lians --env LIANS_MCP_ENABLED_TOOLS=remember,recall,list_memories,correct_memory,forget_memory -- uvx --from "lians-sdk[mcp]" lians-mcp

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Node.js 等运行时,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后随便调一个只读工具,确认能返回结果,再接入正式流程。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
文档检索问答

在你的文档库里按问题找答案。

知识库读写

把新资料写进知识库,随用随取。

内容整理

把零散资料归纳成结构化笔记。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude、Cursor、VS Code,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 资料没标注工具数量,实际能力要装好后确认。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在文档知识场景里让模型直接调用外部能力的人。
  • 已经在用 Claude、Cursor 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Lians Agent Memory当前 未标注 stdio · 本地进程 本地部署 有 未标注
dify 未标注 stdio · 本地进程 本地部署 有 2026-04-11
open-webui 未标注 stdio · 本地进程 本地部署 有 2026-04-11
JeecgBoot 未标注 stdio · 本地进程 本地部署 有 2026-04-11
Cherry Studio 未标注 未标注 未标注 无 2026-05-17
mempalace 未标注 stdio · 本地进程 本地部署 有 2026-04-11

服务器档案

文档知识
字段来自项目仓库与公开索引,中文说明由本站标注
提供方未标注上游标注的维护方 未标注
分类文档知识本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式未标注远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验未标注上游最后核验时间

详细介绍

9.7 KB
来自项目仓库与上游目录的原文,未做删改

Recover the task. Reject stale state. Block unsupported done.

Quickstart ·
Why Lians ·
ContinuityBench ·
Install ·
Docs ·

Lians Guard

The current-state and completion guard for AI coding agents.

Lians recovers interrupted agent work, rejects stale task state, and blocks
done until the current task is ready for human review.

> Your agent can forget the chat. It cannot forget what is finished, what
> changed, or what still has to pass.

  • Recover. Resume a bounded current task across supported Claude Code and
    Codex sessions.
  • Reject stale state. Bind checkpoints to current repository and task state
    so old evidence is not silently reused.
  • Guard completion. Separate measured evidence from an agent's own claims
    and keep the gate closed while work is missing, unknown, failed, or blocked.
  • Require review. READY FOR HUMAN REVIEW is a handoff to a person, never a
    claim that the work is correct, approved, or safe to deploy.
  • Stay local. The free recovery path needs no Lians account, AI password, or
    provider API key.

Lians works with your existing AI account and editor. It does not replace your
model, Git, CI, repository instructions, or human review.

Two layers, one agent loop

The open-source Lians Guard layer lives inside Codex through MCP, skills,
hooks, and repository state. It remembers corrections and exposes evidence
without taking over the model. The optional Lians Mission Control beta is
the local control layer: give it one mission, let it choose a bounded Codex
route, and require a real verifier before it returns PASS.

On supported Codex versions, one Mission Control mission now uses one Codex
app-server thread instead of starting a new process and replaying a summary for
every stage. Codex still owns authentication, tools, sandboxes, and execution;
Lians owns the durable mission, usage policy, and receipt. App-server is
currently experimental, so the one-shot adapter remains available.

Inspect the Mission Control source, read the
bridge boundary, or follow the
external proof-gate protocol.

One clear result after every agent session```text

RECOVERED
Task: Fix OAuth callback handling
Next: Re-run the callback integration test

STALE
Reason: The authentication requirement changed after this checkpoint

BLOCKED
Missing: OAuth callback integration test
Untrusted: "tests passed" was reported by the agent, not measured

READY FOR HUMAN REVIEW
Measured locally: callback tests passed
Measured by CI: required checks passed


The trust model is deliberately strict. `measured_local`, `measured_ci`, and
`human_confirmed` evidence can satisfy a criterion. `agent_attested` and
`inferred_activity` records remain useful context but cannot open the review
gate. An agent cannot promote its own checkpoint into a trusted class. Trusted
CI evidence requires an exact GitHub attestation and commit match plus an
interactive check-to-criterion mapping; human evidence requires interactive
confirmation. Read why Lians exists, the full
Lians Guard product contract, and the current market
pressure test.

## Try it in two minutes

Choose the AI tool you already use:

| Tool | Fastest setup |
|---|---|
| Codex app, CLI, or IDE | One command |
| Claude Code | Two plugin commands |
| Cursor | One-click MCP install |
| Other MCP clients | Minimal MCP setup |

For example, after installing `uv`, connect Codex with:```bash
codex mcp add lians --env LIANS_MCP_ENABLED_TOOLS=remember,recall,list_memories,correct_memory,forget_memory -- uvx --from "lians-sdk[mcp]" lians-mcp

Restart Codex, then save one safe project fact and recover it in a fresh chat.
Local memory is stored in ~/.lians/mcp.db by default. This is the available
free recovery path; the full Guard workflow is currently a developer preview.

Follow the complete quickstart for setup, recovery,
correction, deletion, and the Guard preview boundary.

What a fresh coding agent receives

Lians can generate a bounded project handoff instead of replaying a transcript:```text
Reported complete; verify:
- migrated the orders API to /v2/orders

Still open:
- verify the migration against current Git state
- update documentation

Decisions:
- keep pytest

Changed:
- /v1/orders is stale; use /v2/orders

Next:
- update documentation before touching unrelated UI


The handoff is derived from current Lians state, not a manually maintained
summary. Agent-reported work remains visible without being mislabeled as
verified completion.

## Why this is not another generic memory layer

Native memories are convenient when work stays inside one product. General
memory is no longer a scarce category. Lians uses local memory for recovery,
then focuses on the expensive gap: current task state and evidence-backed
readiness.

The current competitive landscape pressure
tests this position against native Claude Code, Codex, Cursor, GitHub Copilot,
Entire, Factory, and AI review workflows.

| Approach | Best fit | Boundary |
|---|---|---|
| Native tool memory | One AI tool, minimal setup | Usually stays inside that vendor |
| `AGENTS.md` or `CLAUDE.md` | Stable repository instructions | Must be maintained manually |
| Transcript replay | Reconstructing one conversation | Large, noisy, and may revive stale decisions |
| Free Lians recovery | Resume current project context across supported tools | Requires a local connection to each tool |
| Lians Guard | Detect stale state and gate readiness with typed evidence | Team workflow is still in developer preview |

Lians is not claiming that every project needs a separate memory layer. See the
honest comparison and decision guide.

## Project status

Lians is under active development. Available recovery features and preview Guard
features are separated here so the repository does not imply a production
guarantee that does not exist yet.

| Capability | Status |
|---|---|
| Local memory through MCP and Python | Available |
| Codex, Claude Code, and Cursor local recovery setup | Available |
| Inspect, correct, and confirmed permanent deletion | Available |
| Bounded context and signed selection receipts | Available |
| Automatic Claude-to-Codex project handoff | Beta |
| Typed evidence and evidence-backed task gate | Developer preview |
| Local Git workspace fingerprint on checkpoints | Developer preview |
| Automatic stale evidence invalidation | In development |
| Attested GitHub Actions evidence intake | Developer preview |
| Local Guard reporting | Developer preview |
| Shared team queue | Planned |
| Cross-platform clean-install CI | Required by the new Guard workflow; first hosted run pending |
| Guided desktop installer and local control center | Release candidate |
| Mission Control Protect-versus-Maximum beta | Candidate; proof gate preregistered |
| Persistent one-mission/one-Codex-thread bridge | Beta; app-server is experimental |

The macOS and Windows desktop builds remain release candidates pending platform
signing and notarization. See the desktop preview boundary.

## Current evidence

The included Claude-to-Codex continuity fixture recovered **10/10 expected
facts**, exposed **0 stale facts as current**, and produced a **231-token
handoff**. These are bounded beta results, not a promise that every live coding
session extracts perfectly. Run the experiment.

The developing ContinuityBench v0.1
publishes the proposed cross-agent, freshness, correction, erasure, provenance,
and boundedness test contract. Its current Lians fixture is evidence for that
fixture only; it is not presented as a completed competitor leaderboard.

A separate live test saved a synthetic project fact through Cursor, recalled it
in a new Cursor chat and a fresh Claude Code session, and confirmed it was gone
after deletion. Read the test method.

The Guard correctness benchmark exercises missing evidence, unknown criteria,
failed constraints, blockers, stale updates, and drift signals. It is a local,
deterministic test of the configured policy, not proof of semantic correctness
or a production outcome. Run `packages/lians-easy/benchmarks/task_contract_correctness.py`
to inspect the cases.

## Build with Lians

Use the local Python SDK inside an application:```bash
pip install "lians-sdk[local]"
``````python
from datetime import datetime, timezone
from lians import LocalLiansClient

memory = LocalLiansClient(db_path=".lians/memory.db")
memory.add(
    agent_id="my-agent",
    content="The project uses Python 3.12 and pytest.",
    event_time=datetime.now(timezone.utc),
)

result = memory.recall(
    agent_id="my-agent",
    query="Which Python version and test runner should I use?",
)

See the install guide for TypeScript, Go, Java, C, framework
integrations, and self-hosting.

Running a class, club, hackathon, or campus developer group? Use the
student and community kit. Contributors and
package integrators can start with
Supported paths and repository status.

Advanced capabilities

Lians also includes tools for project-scoped agent handoffs, signed selection
and review receipts, local research and browser briefs, temporal reconstruction,
lineage, information barriers, confirmed erasure, and bounded formal checks.
These capabilities are useful for advanced or governed deployments but are not
required for the starter memory workflow.

  • Memory engine
  • Cross-agent continuity experiment
  • Agent-work verification
  • Security model
  • Community and managed product boundary
  • Supported paths and repository status

Development```bash

git clone https://github.com/Lians-ai/Lians.git
cd Lians
python -m pip install -e ".[dev]"
python scripts/test_all.py
```

Read CONTRIBUTING.md before opening a pull request. Feature
ideas, integration requests, and reproducible bugs are welcome in
GitHub Issues.

If Lians helps your workflow, star the repository
so other AI-tool users can find it.

License

Apache 2.0. See LICENSE.

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Lians Agent Memory 怎么安装?

在客户端按下面的安装命令接入:codex mcp add lians --env LIANS_MCP_ENABLED_TOOLS=remember,recall,list_memories,correct_memory,forget_memory -- uvx --from "lians-sdk[mcp]" lians-mcp。装完在客户端配置里引用同一个包或端点。

Lians Agent Memory 怎么在 Claude、Cursor、VS Code 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Lians Agent Memory 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Lians Agent Memory 需要 API Key 吗?

资料没有标注鉴权方式,是否需要密钥取决于服务本身,接入前按官方文档确认。

Lians Agent Memory 支持哪些客户端?

资料标注支持 Claude、Cursor、VS Code、Gemini CLI、Codex、Zed;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Lians Agent Memory 能提供哪些能力?

资料显示能力标签包括 记忆。具体工具清单以官方文档为准。

Lians Agent Memory 需要什么运行环境?

属于本地进程,需要在本机装好运行环境。

Lians Agent Memory 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 未标注。