Tell Claude once. Cursor already knows.Skip the recap and keep building.
LinkLore keeps one shared note of your project — decisions, dead ends, rules — so every agent you already use has the context, without repeating it.
One memory, for all agents. No more per-agent memory files to keep in sync.
COMPATIBLE AGENTS
Claude CodeCursorWindsurfGemini CLICodex+ any MCP client
Three outcomes that end the project recap.
› brief() → context restored · 0.8s ✓
brief()
Instant recall
One call restores the whole project context in a new session.
⚠ drift — auth.py changed since lr-f3a4b5c6
drift
Code-linked memory
When linked code changes, memory knows.
› push → backend-team ✓
push · pull
Team sync
Share memory across teammates and projects with push/pull.
The honest comparison
LinkLore vs. Claude Code's built-in memory vs. Plain markdown
Pick an axis to see how the three actually compare. No spin, caveats included.
LinkLore
✓
add() checks new entries against existing ones and flags contradictions instead of letting them silently coexist.
Claude Code built-in memory
✕
Nothing checks the memory file against what's currently true. It can state something already-corrected and never catch up.
Plain markdown
✕
Fully manual. A stale note sits there looking just as confident as a current one.
Real usage, real tools
What agents actually say mid-session
Real feedback from dogfooding sessions and outside AI reviewers. No logos, just the actual words.
Tax SaaSDogfood
Lore saved us from repeating the same design debates. The rejection rationale from 3 months ago was still there.
— ongoing use
Accounting automationDogfood
One brief() call and I had the full project context. Nothing like reading 5 scattered .md files.
— ongoing use
External AI reviewerAI review
Flat markdown would cost 300–500K tokens. Each call costs 200 to 3,000. That's 100 to 1,000x.
— token-economy review
Tax SaaSDogfood
One brief() call at session start and I never ask 'what were we doing?' again.
via brief()
Grok 4.5 highAI review
The core delivers — brief() alone is worth it.
— first session, on Cursor
Tax SaaSDogfood
Lore saved us from repeating the same design debates. The rejection rationale from 3 months ago was still there.
— ongoing use
Accounting automationDogfood
One brief() call and I had the full project context. Nothing like reading 5 scattered .md files.
— ongoing use
External AI reviewerAI review
Flat markdown would cost 300–500K tokens. Each call costs 200 to 3,000. That's 100 to 1,000x.
— token-economy review
Tax SaaSDogfood
One brief() call at session start and I never ask 'what were we doing?' again.
via brief()
Grok 4.5 highAI review
The core delivers — brief() alone is worth it.
— first session, on Cursor
Academic reviewAI review
Lore = history, code = current invariant. This distinction is what lets AI make real decisions.
— ongoing use
External AI reviewerAI review
I don't have to remember to search — it just interrupts me with what's relevant.
— token-economy review
Internal dogfoodDogfood
Git tells me what changed. Lore tells me why. That cross-reference has no substitute.
— self-review
Academic reviewAI review
After every non-trivial decision, add() became muscle memory. Three months later, the lore pays for itself.
via add()
Academic reviewAI review
Tag discovery with show(tag='?') was a game changer for onboarding.
via show()
Academic reviewAI review
Lore = history, code = current invariant. This distinction is what lets AI make real decisions.
— ongoing use
External AI reviewerAI review
I don't have to remember to search — it just interrupts me with what's relevant.
— token-economy review
Internal dogfoodDogfood
Git tells me what changed. Lore tells me why. That cross-reference has no substitute.
— self-review
Academic reviewAI review
After every non-trivial decision, add() became muscle memory. Three months later, the lore pays for itself.
via add()
Academic reviewAI review
Tag discovery with show(tag='?') was a game changer for onboarding.
via show()
Install in three steps. Then it's automatic.
01 · TELL YOUR AGENT:Tell your agent. It reads install.md and sets everything up.
02Work as usual. Your agent records lore as it goes.
03
› brief() → context restored
Next session, it already knows. Try each tool below.Manual setup (no web access, or you'd rather see it first)
$ claude mcp add llre -- uvx llre
Cursor, Gemini CLI, and Codex use the same uvx llre command in each client's MCP config. Details: linklore.io/install.md
- brief()
- add()
- show()
- edit()
- link()
- status()
- log()
- push · pull
- +13 others
brief()
3 MONTHS FREE
Memory you query, not maintain.
Launched July 27. 3 months free as a launch special. Early users keep a free tier.
FREE
$0
Fully free, local
PRO
$7.9/mo
Start sharing with your team in OpenBox