v1.2.0-beta Graph-Augmented Hybrid Memory Engine beta · Invite/cap controlled · Not GA
LOCAL ALPHA OPENREST APIMCP STDIOPOSTGRES 16DASHBOARDPRIVATE DEPLOY

Lore Context.

O plano de controle para memória de agentes de IA.

Veja o que cada agente lembrou, usou e deve esquecer antes que memória vire risco de produção.

Executar alpha local → View on GitHub ↗
$ pnpm quickstart -- --dry-run --activation-report
Golden clients3
MCP tools11
Demo eval size4
Latencypending
lore › context.ledger local · demo fixture
Demo memories4public fixture
Golden clients3Claude · Cursor · Qwen
Trace rows2retrieved and used
P95 latencypendingnot claimed
sourcememoryevidenceused_in_responsestale_scoresensitivityreview_status
claude-code#a4f1api-contractyes lowapproved
cursor#b2c8pricing-noteyes lowapproved
qwen-code#c9d3deploy-fixyes medflagged
hermes#d1a7private-keyyes highredact
fastgpt#f3c1old-schemano medreview
context.compose()
demo eval
policy pass
trace linked
k 5
gov · gate
memory#a4f1STALESENSITIVE
demo-private · audit_loglocal alpha · public fixture
Multiple coding agents

Share governed context across Claude Code, Cursor, Qwen Code, and local agents.

Audit agent memory

Open a trace and see which rows were retrieved, used, ignored, stale, or risky.

Migrate memory later

Use MIF-style export fields for provenance, supersedes, and contradicts relationships.

01 / PROBLEMThe memory gap

Agentes lembram. Equipes precisam de prova.

A memória longa cresce, mas poucas equipes conseguem mostrar a trilha de auditoria de uma resposta.

01
14d agonow

Problema

A memória longa cresce, mas poucas equipes conseguem mostrar a trilha de auditoria de uma resposta.

02
? doc?user?run?when?

Recursos

Cada capacidade é inspecionável, automatizável e desligável.

03
agent !memory

Avaliação

Acompanhe recall, precision, stale-hit e latency ao alterar recuperação.

04
pgvecqdrantweav.milvus

Integrações

Lore expõe MCP stdio e REST pela mesma camada de governança.

02 / SYSTEMPipeline

Um caminho governado entre agentes e memória.

Lore avalia recuperação, rastreia respostas e envia gravações arriscadas para revisão.

System diagram · context plane v0.6read path · policy gate · persist + audit
MCP CLIENTSSDK · STDIOCOMPOSERCONTROLPERSISTENCE claude-codecursorqwen-codehermesdify CALLcontext.query()k:5 · ttl:24h · scope:repo COMPOSEcontext.compose() retrieve() k=12rerank() localpolicy() redact 2trace() linkedreturn 5 / 12 evalrecall@5 · precision · MRRtracespan tree · per-source · p95governancepolicy · redact · review RDStruth · audit · lifecycleQdrant derived index agentmemoryqdrant · weaviate · pgvec
01MCP clients

Lore expõe MCP stdio e REST pela mesma camada de governança.

02context.query

Cada capacidade é inspecionável, automatizável e desligável.

03composer

Lore avalia recuperação, rastreia respostas e envia gravações arriscadas para revisão.

04eval / trace / governance

Acompanhe recall, precision, stale-hit e latency ao alterar recuperação.

05Postgres + adapter

Lore expõe MCP stdio e REST pela mesma camada de governança.

03 / FEATURESProduct surfaces

Seis superfícies de produto. Uma auditoria.

Cada capacidade é inspecionável, automatizável e desligável.

F · 01context.query
› context.query("auth flow", k:5)

Context Query

Cada capacidade é inspecionável, automatizável e desligável.

stdio · httpk=1..32ttl-aware
F · 02eval.run
smoke run → report · public safe

Memory Eval Playground

Acompanhe recall, precision, stale-hit e latency ao alterar recuperação.

recall@5precision@5MRR
F · 03observability
composeretrievererank

Memory Observability

Lore avalia recuperação, rastreia respostas e envia gravações arriscadas para revisão.

span treeper-agentp50/p95/p99
F · 04governance
+ memory#a4f1+ scope:repo- secret redactedapproveredactdeferreject

Governance Review

A memória longa cresce, mas poucas equipes conseguem mostrar a trilha de auditoria de uma resposta.

policy.loreapprove/rejectdiff view
F · 05export.mif
loremif pack⇆qdrantreplay

MIF-like Portability

Lore expõe MCP stdio e REST pela mesma camada de governança.

JSON Lines.lore.tarreplay()
F · 06deploy.local
your networklore-apidashboardpostgres⊘

Private Deployment

Quatro comandos, dados demo e um smoke test Playwright do dashboard.

docker composeair-gappedBYO Postgres
04 / ALPHAShipped this week

O que há no v0.6 alpha.

Lista honesta. Roda localmente com Docker Compose.

✓Graph-Augmented Hybrid Memory Engine betaPostgres FTS + pgvector hybrid recall, v12 episode/item/chunk schema, Postgres temporal graph, lifecycle propagation, v12 eval gate / production gate1.2.0-beta
✓Cloud Memory Engine betaGoogle sign-in, automatic capture, SQS worker fan-out, RDS truth store, Qdrant hybrid recall, Memory Inbox exceptions, and Evidence Ledger1.1.0-beta
✓REST API + OpenAPI/v1/context, /v1/memory, /v1/eval — documented at /openapi.jsonv0.6.0
✓MCP stdio SDK transportDrop-in for any MCP-compatible clientmcp 0.6
✓Evidence LedgerTrace-centric proof of retrieved, used, ignored, and risky memoryledger
✓Activation reportDry-run and real first-value proof with redacted local evidenceactivation
✓AI-readable docs/llms.txt, /llms-full.txt, canonical metadata, and public-source boundariesllms
✓Public-safe evalShare metrics without raw memory content or dataset messageseval
✓Distribution packMCP registry, agent plugin, marketplace, and launch content draftsdocs
✓Design partner intakeIssue template, intake rubric, and activation scorecardintake
◐Public SaaSHosted multi-tenant sync, billing, and remote MCP HTTP stay out of v0.6roadmap

Build manifest

1.2.0-beta · 04.05.2026
graph beta
v1.2 graph-augmented hybrid memory engine
public release
v1.2.0-beta formal pre-release
runtime
node 22+ · RDS 16 · Qdrant
smoke
passing · production smoke
bundle
static website · Docker images
memory floor
RDS truth · Qdrant index
telemetry
privacy-safe
license
Apache 2.0
# first rungit clone github.com/Lore-Context/lore-context
pnpm install && pnpm quickstart -- --dry-run --activation-report
pnpm openapi:check # release gate
05 / EVALMethodology

Prova de avaliação nos seus dados.

Acompanhe recall, precision, stale-hit e latency ao alterar recuperação.

prod/smoke-2026-05-04OpenAPI · Hosted MCP · OAuth start · Dashboard · LLM files · no benchmark claimPUBLIC · v1.2.0-beta · memory engine
Recall@51.0004-item smoke dataset vs baseline
Precision@50.200expected with k=5 vs baseline
MRR0.875one query ranked #2 vs baseline
Stale-hit0.000no stale demo rows vs baseline
p95 latencypendingnot measured via MCP vs baseline

What the smoke run proves

pipeline retrieves gold memorypass
Evidence Ledger trace is inspectablepass
stale rows are reported as zeropass
larger dataset still requiredtodo
latency must be measured via direct APItodo

Publication guardrails

4-item datasetsmall
no LOCOMO claimtrue
no p95 claimtrue
raw data archivedyes
methodology firstyes
Use this as methodology, not a benchmark win.Read report →
06 / INTEGRATIONSDrop-in MCP

Fale os protocolos que seus agentes já usam.

Lore expõe MCP stdio e REST pela mesma camada de governança.

CLClaude Codemcp.stdio · alpha
CUCursormcp.stdio · alpha
QWQwen Codemcp.stdio · alpha
OPOpenClawmcp.stdio · alpha
HEHermesmcp.stdio · alpha
DIDifyrest.v1 · alpha
FAFastGPTrest.v1 · planned
RORoo Coderest.v1 · planned
OPOpenWebUIrest.v1 · planned
LOLocal agentsrest.v1 · planned
07 / STARTStart

Comece com um alpha local. Prove a qualidade da memória antes de escalar.

Quatro comandos, dados demo e um smoke test Playwright do dashboard.

Executar alpha local →Ver arquitetura
$ git clone https://github.com/Lore-Context/lore-context
$ cd lore-context
$ pnpm install
$ pnpm quickstart -- --dry-run --activation-report
$ pnpm openapi:check
$ pnpm smoke:dashboardverified · OpenAPI · evidence · smoke passing