Lians Agent Memory
About
Bitemporal agent memory with point-in-time retrieval, supersession, audit trails, and regulated-memory controls.
Details
- Author
- lians-ai
- Categories
- AI
Jump to
Setup
Install Lians Agent Memory in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/lians-ai/Lians
Follow the installation instructions in the repository README, then restart your MCP client.
Recover the task. Reject stale state. Block unsupported done.
Quickstart·Why Lians·ContinuityBench·Install·Docs·Issues
The current-state and completion guard for AI coding agents.
Lians recovers interrupted agent work, rejects stale task state, and blocksdoneuntil 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 REVIEWis 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.
One clear result after every agent session
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, andhuman_confirmedevidence can satisfy a criterion.agent_attestedandinferred_activityrecords 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. Readwhy Lians exists, the fullLians Guard product contract, and the currentmarket pressure test.
For example, afterinstallinguv, connect Codex with:
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.dbby default. This is the available free recovery path; the full Guard workflow is currently a developer preview.
Lians can generate a bounded project handoff instead of replaying a transcript:
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.
Lians is not claiming that every project needs a separate memory layer. See thehonest comparison and decision guide.
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.
The macOS and Windows desktop builds remain release candidates pending platform signing and notarization. See thedesktop preview boundary.
The included Claude-to-Codex continuity fixture recovered10/10 expected facts, exposed0 stale facts as current, and produced a231-token handoff. These are bounded beta results, not a promise that every live coding session extracts perfectly.Run the experiment.
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. Runpackages/lians-easy/benchmarks/task_contract_correctness.pyto inspect the cases.
Use the local Python SDK inside an application:
pip install "lians-sdk[local]"
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 theinstall guidefor TypeScript, Go, Java, C, framework integrations, and self-hosting.
Running a class, club, hackathon, or campus developer group? Use thestudent and community kit. Contributors and package integrators can start withSupported paths and repository status.
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
git clone https://github.com/Lians-ai/Lians.git cd Lians python -m pip install -e ".[dev]" python scripts/test_all.py
ReadCONTRIBUTING.mdbefore opening a pull request. Feature ideas, integration requests, and reproducible bugs are welcome inGitHub Issues.
If Lians helps your workflow,star the repositoryso other AI-tool users can find it.
Local-first agent memory: a plain-Markdown Obsidian vault is the source of truth, with a rebuildable DuckDB index for hybrid BM25 + vector + graph recall.
Persistent memory and semantic search for AI coding assistants across sessions
Give your agent a memory: shared, cited, tenant-isolated knowledge-graph memory for any MCP host. Grounded answers from a local-first June endpoint — abstains rather than guesses.
Decentralized persistent memory for AI agents — encrypted vault storage built on Walrus and Sui.
Persistent memory for AI assistants and coding agents across ChatGPT, Claude, Cursor, and other MCP-compatible tools.
Your portable AI memory vault — memories, skills & configs, shared across every AI tool.
Local Work Model for AI agents that learns from real outcomes.
Adaptive MCP memory system for AI applications. Learns which retrieval strategies work for your data, scores results using cognitive science models, builds a knowledge graph automatically, and validates every parameter change against real query history before adopting it. Patent pending.
Auditable, self-improving knowledge & memory for AI agents over MCP — citation-enforced answers and a replayable why-trace, self-hosted on Postgres.
Turns your task manager into agent memory: hybrid (RRF) retrieval over TickTick or an Obsidian vault via an adapter contract. MCP server + CLI, no vector DB to maintain.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
