Labsco
gowtham0992 logo

Link

★ 80

from gowtham0992

Local Markdown memory for AI agents

🔥🔥🔥✓ VerifiedFreeAdvanced setup
#email#automation#git#security#memory

Link

Local memory for AI agents.

Link gives Codex, Claude, Cursor, Kiro, VS Code, Copilot, Antigravity, and other local agents the same source-backed memory, stored locally as Markdown.

Website · How it works · Memory · Tools & CLI · Setup · Docs · MCP Registry · PyPI · Homebrew

What Is Link?

Link is an open-source memory layer for local AI agents. Raw sources become an inspectable Markdown wiki. Explicit "remember this" requests become reviewable memories. Agents retrieve compact, source-backed context through the CLI, MCP, official skills, or the local viewer without dumping the whole wiki into a chat window.

The wiki is the storage layer. The product is durable memory that stays on your machine, remains readable in plain files, and can be shared across multiple agents instead of locked inside one vendor profile.

How It Works

Link gives agents four simple moves:

  • Capture notes, transcripts, docs, screenshots, and project context in raw/.

  • Structure source-backed pages under wiki/.

  • Remember explicit preferences, decisions, facts, and project context as reviewable memory.

  • Retrieve compact query packets through the CLI, MCP, official skills, or the local web viewer.

Most agent sessions start from zero. You re-explain preferences, repo decisions, project constraints, and why something matters. Link turns that repeated context into local memory agents can query.

Pain Link's answer Agents forget you between sessions. Save reviewed preferences, decisions, facts, and project context. Notes are private or messy. Keep raw sources local, then turn them into source-backed Markdown. Context windows are expensive. Return compact query packets with provenance and follow-up actions. Memory needs trust. Every page and memory can be inspected, reviewed, archived, or forgotten.

Link follows Andrej Karpathy's LLM Wiki pattern: keep knowledge outside the chat window, make claims inspectable, and let context compound over time.

Ways To Use Link

Pick the surface that matches how you work. They all read and write the same local Markdown wiki.

These surfaces are independent. lnk serve / serve.py is only the local web viewer. CLI commands, official skills, and MCP tools read the same wiki/ files directly, so Claude, Codex, Kiro, Cursor, or another agent can use Link even when the web viewer is not running.

Web UI Read the local wiki, then review memory, ingest, graph, audits, captures, and explanations.

CLI Script readiness, query packets, briefs, validation, backup, benchmark, and repair.

MCP Let Codex, Claude, Cursor, Kiro, VS Code, Copilot, and other agents recall memory.

The local web viewer: browse source-backed memory and explore the knowledge graph — all on 127.0.0.1, no accounts, no backend.

Prefer skills instead of MCP? Link ships small, lazy-loadable CLI skills under skills/. They let an agent use lnk health, lnk query, lnk ingest-status, and lnk remember directly, without MCP setup or a running web viewer.

Copy & paste — that's it
skills/link-health/SKILL.md
skills/link-retrieve/SKILL.md
skills/link-ingest/SKILL.md
skills/link-memory/SKILL.md

Full guide: Link Skills.

Storage Model

Under the hood, Link separates source-backed knowledge from durable agent memory:

  • Drop raw notes, transcripts, articles, and project context into raw/.

  • Agents compile those sources into inspectable pages under wiki/.

  • Explicit "remember" requests become reviewable memory pages.

  • Queries retrieve compact agent context from both the wiki and memory layer.

The storage model is plain and inspectable:

Layer What lives there raw/ Original notes, transcripts, articles, PDFs, screenshots, and project files. wiki/ Source-backed pages, concepts, entities, explorations, comparisons, and memories. Agent interfaces CLI, skills, MCP, and local viewer paths that avoid dumping the whole wiki into context.

If a raw file was already ingested and later edited, lnk ingest-status marks it as stale and tells your agent to refresh the existing source page instead of creating a duplicate.

What Agents Get

When an agent uses Link through MCP, these are the stable tools it receives. CLI and skill workflows call the same core behavior through lnk.

  • query_link: an answer-ready packet with relevant memories, pages, graph neighborhood, reasons for selection, budget limits, and follow-up actions.

  • memory_brief: a compact pre-work brief with user/project preferences, active context, review warnings, and safe memory-use rules.

  • ingest_status: exact next steps for raw files, including source safety, stale ingest detection, validation, and memory proposal guidance.

  • remember_memory: durable local memory with duplicate/conflict checks, visibility sharing intent, review state, optional review_after re-check dates, optional expires_at expiry dates, provenance, and audit logging.

  • set_memory_visibility: explicit post-review sharing changes between private, project, and team visibility without editing Markdown by hand.

  • explain_memory: why a memory exists, what it links to, whether it is ready for recall, and what needs review.

  • memory_log: recent memory lifecycle changes from wiki/log.md, without raw source or memory bodies.

  • memory_wins: local proof signals for what Link memory is carrying, based on wiki metadata rather than telemetry.

The stable agent-facing loop is documented at Link Memory Contract: readiness first, bounded recall, explicit memory writes, audit tools, and sharing semantics.

Use review_after for time-sensitive preferences or decisions. When that date arrives, the memory reappears in Link's review inbox so an agent can ask the user to confirm, update, archive, or forget it instead of trusting stale context. Use expires_at for temporary context that should automatically leave default recall after a date; Link keeps the Markdown page inspectable and asks the user to update, archive, or delete it. Use visibility to separate where a memory applies from who should see it: private stays personal, project is intended for a project workspace, and team means the user explicitly approved sharing it with a team.

For team handoff or security review, lnk compliance-export --output audit.json writes a redacted JSON packet with readiness, validation, memory review status, operation markers, and recent audit log entries. Raw source contents and memory bodies are not included.

For day-to-day auditability, lnk memory-log ~/link shows what Link recently remembered, updated, reviewed, archived, restored, forgot, or accepted from raw captures.

For recovery, lnk backup ~/link creates a local archive and lnk restore-backup <archive> ~/link previews what would be restored. Passing --confirm replaces local files after creating a safety backup when possible; raw/ is still excluded unless --include-raw is explicit.

For local proof of value, lnk wins ~/link shows reusable memories, reviewed memory, provenance, project continuity, freshness guardrails, and copyable prompts without tracking user behavior.

For Git-backed team memory, lnk team-sync ~/link checks whether the workspace is ready to share reviewed wiki/ pages while keeping raw/, caches, backups, and local MCP Python markers private by default. It also blocks "ready" status when the memory inbox is not clear or active visibility: private memories would be included by a broad git add wiki.

Copy & paste — that's it
lnk team-sync ~/link --remote [email protected]:team/link-memory.git

For a teammate, reviewer, or another agent, lnk share resolves a page, memory, title, alias, or search phrase into a local viewer URL:

Copy & paste — that's it
lnk share "Prefer local memory" ~/link

For a static, read-only review packet, lnk snapshot exports rendered wiki HTML without raw/, captures, operation markers, live MCP state, or memory pages by default. --include-memories exports only non-private memories; use --include-private-memories only for a personal archive or an explicitly approved review. It blocks export if wiki pages contain secret-looking values unless you explicitly override it.

Copy & paste — that's it
lnk snapshot ~/link --output link-snapshot
lnk snapshot ~/link --output link-snapshot --include-memories --force
lnk snapshot ~/link --output personal-snapshot --include-memories --include-private-memories --force

Agent Contract

For MCP clients, agents should use Link in this order:

  • link_status to check readiness and safe next actions.

  • starter_prompts when the user asks what to try first.

  • ingest_status before touching raw sources.

  • query_link for compact answer-ready context.

  • memory_brief before longer work.

  • get_graph_summary when graph context is useful but the full graph would be noisy.

  • backup_wiki before broad repair or migration work.

  • validate_wiki after ingest or broad wiki edits.

Full MCP tool list: MCP setup.

Privacy And Safety

Link itself is local-first:

  • No telemetry in the installed CLI, MCP server, local web UI, or wiki runtime.

  • No hosted backend.

  • No external API calls from serve.py or link-mcp.

  • Raw sources and generated wiki pages are ignored by git by default.

  • lnk backup excludes raw/ unless you explicitly pass --include-raw.

  • Secret-looking API keys, provider tokens, JWTs, registry credentials, and private key blocks are detected in raw sources, captures, and release hygiene checks. lnk validate and lnk doctor also fail if secret-looking values are found inside wiki pages before they can be served through the local UI or returned through agent context.

  • The local web server binds to 127.0.0.1 and is not meant to be exposed to the internet without additional auth.

Before sharing a repo, demo, or wiki:

Copy & paste — that's it
python3 link.py doctor
python3 link.py validate
python3 scripts/check_release_hygiene.py

More detail: Security guide.

Documentation

Need Go here Run Link for the first time First 10 minutes Decide whether Link fits Why Link? Use the local viewer Web UI Understand raw/wiki/memory Concepts Configure MCP MCP setup Find a command CLI reference Use Link without MCP setup Official skills Use local HTTP endpoints HTTP API Review security boundaries Security model Evaluate Link for a small team Team security review Fix setup issues Troubleshooting

Contributing

Contributions should come through pull requests targeting main. The develop branch is a maintainer integration branch for larger release work before it is proposed to main.

Before opening a PR:

Copy & paste — that's it
python3 -m ruff check .
python3 -m pytest tests
python3 scripts/check_release_hygiene.py
python3 scripts/check_runtime_duplication.py
python3 scripts/check_tool_contract.py
git diff --check

Full contributor guide: Contributing.

Do not include personal wiki data, raw sources, registry tokens, .env files, or local MCP credentials in a PR.

If Link helps your agents remember better, star it on GitHub so more people can find it.