NocturnusAI
NocturnusAI
El motor de ingeniería de contexto para agentes de IA: envía solo lo que ha cambiado.

Antes / Después
# ❌ Without NocturnusAI — replay everything, every turn
messages = system_prompt + full_history + tool_outputs # ~1,259 tokens/turn
response = llm(messages) # $13,600/mo at scale
# ✅ With NocturnusAI — send only what changed
ctx = nocturnus.process_turns(raw_turns) # extract → infer → delta
messages = system_prompt + ctx.briefing_delta # ~221 tokens/turn
response = llm(messages) # $2,400/mo. Same accuracy.Related MCP server: RelayPlane
Las cifras
Medido en APIs en vivo. Conversación de soporte de producto de 15 turnos. Recuentos reales de usage.input_tokens. Ejecútalo tú mismo.
Reproducción ingenua | Optimizado con RAG | NocturnusAI | |
Tokens por turno | ~1,259 | ~800 | ~221 |
Coste mensual (1K pet/h, Opus 4, $15/1M) | $13,600 | $12,000 | $2,400 |
Latencia | alta | media | baja |
Preservación de la verdad | no | no | sí |
Claude Opus 4: 5.7× de reducción. Gemini 2.0 Flash: 10.0×. Cálculos completos.
Instalación
pip install nocturnusai # Python
npm install nocturnusai-sdk # TypeScript
docker run -p 9300:9300 ghcr.io/auctalis/nocturnusai:latest # DockerO utiliza el asistente de configuración:
curl -fsSL https://raw.githubusercontent.com/Auctalis/nocturnusai/main/install.sh | bashPor qué los desarrolladores marcan este repositorio
Reducción de tokens reproducible — benchmark en el repositorio, metodología publicada, ejecútalo contra tu propia carga de trabajo
Inferencia determinista — misma consulta, mismo resultado, siempre. Sin deriva de embeddings, sin lotería de similitud de coseno
Mantenimiento de la verdad — retira un hecho, todas las conclusiones derivadas se retiran automáticamente. Sin contexto obsoleto, sin alucinaciones sobre el estado operativo
Se conecta a pilas existentes — LangChain, LlamaIndex, CrewAI, AutoGen, MCP, Vercel AI SDK, OpenAI Agents SDK, Mastra
Comparable frente a la reproducción ingenua — números derivados, no inventados. Cada afirmación se remonta a una celda de notebook
Inicios rápidos de frameworks
Framework | Integración | Enlace |
LangChain / LangGraph |
| |
CrewAI | Contexto con ámbito de tarea por rol de agente | |
AutoGen | Servidor de contexto invocable por cualquier agente | |
MCP | Servidor compatible con especificaciones para Claude Desktop, Cursor, Continue | |
OpenAI Agents SDK | Middleware de contexto, sin modificaciones de herramientas | |
Vercel AI SDK | Adaptador compatible con Edge para Next.js, Nuxt, SvelteKit | |
Python SDK |
| |
TypeScript SDK |
|
Cómo funciona
Tres pasos. Cada turno.
Extraer — turnos de conversación sin procesar → hechos estructurados mediante extracción por LLM
Inferir — la inferencia lógica de encadenamiento hacia atrás encuentra solo los hechos alcanzables desde el objetivo actual del agente
Devolver la diferencia — un
briefingDeltaque contiene solo lo que ha cambiado desde el último turno
Esto no es búsqueda vectorial. No es resumen. Es inferencia determinista en un motor lógico — indexación Hexastore, encadenamiento hacia atrás y mantenimiento de la verdad.
El bucle de trabajo
Se requiere LLM para turnos en lenguaje natural. Los ejemplos a continuación envían turnos de texto sin procesar a través de un LLM para extraer hechos estructurados. Si inicias el servidor sin un proveedor de LLM, los turnos en lenguaje natural devolverán cero hechos. Consulta Inicio rápido para ver las opciones de configuración, o utiliza la sintaxis de predicados (p. ej.,
"customer_tier(acme_corp, enterprise)") que funciona sin ningún LLM.
1. Primera reducción: POST /context
curl -X POST http://localhost:9300/context \
-H 'Content-Type: application/json' \
-H 'X-Tenant-ID: default' \
-d '{
"turns": [
"user: Customer says they are enterprise and blocked on SLA credits.",
"tool: CRM says account is Acme Corp with a 2M ARR contract.",
"agent: Last week support promised to review SLA eligibility.",
"tool: Billing note says renewal is due next month."
],
"maxFacts": 12
}'2. Paso impulsado por objetivos: POST /memory/context
curl -X POST http://localhost:9300/memory/context \
-H 'Content-Type: application/json' \
-H 'X-Tenant-ID: default' \
-d '{
"goals": [{"predicate":"eligible_for_sla","args":["acme_corp"]}],
"maxFacts": 12,
"sessionId": "ticket-42"
}'3. Turnos posteriores: POST /context/diff
curl -X POST http://localhost:9300/context/diff \
-H 'Content-Type: application/json' \
-H 'X-Tenant-ID: default' \
-d '{"sessionId": "ticket-42", "maxFacts": 12}'Devuelve solo las entradas added y removed entre instantáneas.
4. Fin del hilo: POST /context/session/clear
curl -X POST http://localhost:9300/context/session/clear \
-H 'Content-Type: application/json' \
-H 'X-Tenant-ID: default' \
-d '{"sessionId":"ticket-42"}'Elige tu superficie
from nocturnusai import SyncNocturnusAIClient
with SyncNocturnusAIClient("http://localhost:9300") as client:
ctx = client.process_turns(
turns=[
"user: Customer says they are enterprise and blocked on SLA credits.",
"tool: CRM says account is Acme Corp with a 2M ARR contract.",
],
scope="ticket-42",
session_id="ticket-42",
)
diff = client.diff_context(session_id="ticket-42", max_facts=12)
client.clear_context_session("ticket-42")
print(ctx.briefing_delta)import { NocturnusAIClient } from 'nocturnusai-sdk';
const client = new NocturnusAIClient({
baseUrl: 'http://localhost:9300',
tenantId: 'default',
});
const ctx = await client.processTurns({
turns: [
'user: Customer says they are enterprise and blocked on SLA credits.',
'tool: CRM says account is Acme Corp with a 2M ARR contract.',
],
scope: 'ticket-42',
sessionId: 'ticket-42',
});
const diff = await client.diffContext({ sessionId: 'ticket-42', maxFacts: 12 });
await client.clearContextSession('ticket-42');
console.log(ctx.briefingDelta);{
"mcpServers": {
"nocturnus": {
"url": "http://localhost:9300/mcp/sse",
"transport": "sse"
}
}
}Utiliza la herramienta context en cada turno para obtener un conjunto de trabajo clasificado por relevancia. Empareja MCP con los endpoints de contexto HTTP cuando necesites ensamblaje y diferencias impulsados por objetivos.
Qué hay detrás del flujo de trabajo
Cuando necesitas mecanismos de backend, NocturnusAI los proporciona:
Almacenamiento determinista de hechos y reglas
Inferencia de encadenamiento hacia atrás con cadenas de prueba
Mantenimiento de la verdad y manejo de contradicciones
Hechos temporales con
ttl,validFromyvalidUntilMulti-tenencia mediante
X-DatabaseyX-Tenant-IDSuperficies MCP, REST, Python SDK, TypeScript SDK y CLI sobre el mismo motor
Inicio rápido
Docker (más rápido)
docker run -d --name nocturnusai -p 9300:9300 \
--restart unless-stopped \
-v nocturnusai-data:/data \
ghcr.io/auctalis/nocturnusai:latestcurl http://localhost:9300/health # Verify it's runningDocker con Ollama (habilita la extracción en lenguaje natural)
docker run -d --name nocturnusai -p 9300:9300 \
--add-host=host.docker.internal:host-gateway \
-e LLM_PROVIDER=ollama \
-e LLM_MODEL=granite3.3:8b \
-e LLM_BASE_URL=http://host.docker.internal:11434/v1 \
-e EXTRACTION_ENABLED=true \
ghcr.io/auctalis/nocturnusai:latestDesde este repositorio
make up-ollama && make smokeCLI
nocturnusai # Interactive REPL
nocturnusai -e "context 10" # Salience-ranked working set
nocturnusai -e "compress" # POST /memory/compress
nocturnusai -e "cleanup 0.05" # POST /memory/cleanupDocumentación
Documentación completa: nocturnus.ai
El flujo de trabajo de reducción de turnos | |
Turnos sin procesar → optimizar → diferenciar → borrar | |
Endpoints REST y formas de respuesta | |
Métodos de cliente para Python y TypeScript | |
LangChain, CrewAI, AutoGen, MCP y más | |
Reducción de tokens medida en APIs en vivo | |
Cada número, derivado | |
La tubería de extracción → inferencia → delta |
Docker Compose (avanzado)
git clone https://github.com/Auctalis/nocturnusai.git && cd nocturnusai
make up # Server using .env.example defaults
make up-ollama # + Ollama (reuses host or starts bundled)
make up-monitoring # + Prometheus + Grafana
make smoke # Verify health + context endpointConstruir desde la fuente
Requiere JDK 17+.
./gradlew :nocturnusai-server:run # HTTP server on :9300
./gradlew :nocturnusai-cli:run # Interactive REPL (JVM)
./gradlew :nocturnusai-cli:nativeCompile # Build native binary
./gradlew test # Full test suiteContribuir
Consulta CONTRIBUTING.md. Los problemas etiquetados como good first issue son buenos puntos de entrada.
Seguridad
Informa de vulnerabilidades de forma privada a través de GitHub Security Advisories. Consulta SECURITY.md.
Licencia
Business Source License 1.1 (SPDX: BUSL-1.1). Gratuito para uso interno —incluyendo producción interna— dentro de tu propia organización. Ofrecer NocturnusAI o una funcionalidad sustancial como producto/servicio alojado a terceros requiere una licencia comercial (licensing@nocturnus.ai). Se convierte a Apache 2.0 el 19-02-2030. Consulta LICENSE y DISCLAIMER.md.
AVISO LEGAL Y DE SEGURIDAD
NocturnusAI es un motor de razonamiento determinista, pero su salida es tan fiable como los hechos que se le proporcionan.
Sin garantía de verdad. "Verificado" se refiere a la consistencia lógica de la inferencia, no a la precisión de las afirmaciones del mundo real.
No apto para decisiones autónomas de alto riesgo. No utilices este motor para decisiones médicas, financieras, legales o de seguridad física sin supervisión sin un paso de verificación humana independiente.
Solo capa lógica. NocturnusAI proporciona información e inferencia; no ejecuta acciones.
Sin responsabilidad. Consulta DISCLAIMER.md y LICENSE.
Available Tools
16 toolsaggregateA
Compute aggregations over matching facts. Supports COUNT, SUM, MIN, MAX, and AVG over a numeric argument at a specified position. Example: COUNT all score(player, ?) facts, or AVG scores at argIndex=1. Side effects: none (read-only). Auth: requires X-Tenant-ID header; FACT_READ permission when auth is enabled. Rate-limited per principal. Errors: VALIDATION_ERROR on unknown operation or missing argIndex for numeric ops.
Inputs: predicate (required), args (required), operation (required), argIndex, +1 more.
askA
Query the knowledge base using multi-step logical reasoning (backward chaining with unification). Finds all provable answers by applying rules and matching facts. Use ?-prefixed variables for unknowns; optionally returns full proof chains. Side effects: none (read-only). Auth: requires X-Tenant-ID header; FACT_READ permission when auth is enabled. Rate-limited per principal. Errors: VALIDATION_ERROR on bad args; result set bounded by INFERENCE_MAX_RESULTS (default 10,000) to prevent OOM.
Inputs: predicate (required), args (required), scope, withProof, +1 more.
bulk_assertA
Assert multiple facts in a single call for efficiency. Non-transactional: each fact is attempted independently — contradictions are reported without aborting the batch. Returns counts of successful and failed assertions. Side effects: mutates state (additive) — partial successes persist even if other facts in the batch fail. Auth: requires X-Tenant-ID header; FACT_WRITE permission when auth is enabled. Rate-limited per principal. Errors: VALIDATION_ERROR on malformed input; per-fact failures returned in the response's errors array.
Inputs: facts (required).
cleanupA
Run memory decay and eviction. Expires facts past their TTL and evicts low-salience facts when memory exceeds capacity. Call periodically in long-running agent sessions to prevent unbounded growth. Side effects: DESTRUCTIVE — permanently removes evicted and expired facts (irreversible). Auth: requires X-Tenant-ID header; FACT_WRITE permission when auth is enabled. Rate-limited per principal. Errors: VALIDATION_ERROR on bad threshold.
Inputs: threshold.
compressA
Run memory consolidation: detects repeated episodic patterns (e.g., 'user asked about X five times') and creates semantic summaries. Reduces memory footprint in long-running sessions while preserving essential knowledge. Side effects: mutates state (additive) — creates new summary facts; original facts remain intact. Auth: requires X-Tenant-ID header; FACT_WRITE permission when auth is enabled. Rate-limited per principal. Errors: VALIDATION_ERROR on bad args.
Inputs: no named parameters.
contextA
Get the most relevant knowledge for the current reasoning step, ranked by composite salience (recency × frequency × priority). Returns a token-optimized context window in 'predicate', 'natural', or 'structured' format. Pass goals for goal-driven selection, sessionId for incremental diffs across turns. Side effects: read-only for stored facts (salience access counters may update internally). Auth: requires X-Tenant-ID header; FACT_READ permission when auth is enabled. Rate-limited per principal. Errors: VALIDATION_ERROR on bad args.
Inputs: maxFacts, minSalience, predicates, scope, +6 more.
delete_scopeA
Delete a named scope and all facts within it. Use to clean up completed or abandoned hypothetical reasoning branches. Side effects: DESTRUCTIVE and IRREVERSIBLE — permanently removes all facts in the scope; cascades TMS retraction for any derived facts. Auth: requires X-Tenant-ID header; FACT_WRITE permission when auth is enabled. Rate-limited per principal. Errors: VALIDATION_ERROR if scope name is blank.
Inputs: scope (required).
forgetA
Retract a fact from the knowledge base. Inverse of 'tell'. Side effects: DESTRUCTIVE — triggers cascading retraction of any knowledge derived from this fact via the Truth Maintenance System (irreversible). Auth: requires X-Tenant-ID header; FACT_WRITE permission when auth is enabled. Rate-limited per principal. Errors: VALIDATION_ERROR on bad args (no error if the fact was not present).
Inputs: predicate (required), args (required), scope.
fork_scopeA
Fork a knowledge base scope — creates an independent copy of all facts in the source scope under a new target scope name. Use for hypothetical reasoning ('What if Alice moves to London?') without modifying the main knowledge base. Similar to git branch for knowledge. Side effects: mutates state (additive) — creates a new scope with copied facts; source scope is unchanged. Auth: requires X-Tenant-ID header; FACT_WRITE permission when auth is enabled. Rate-limited per principal. Errors: VALIDATION_ERROR if targetScope is blank or already exists.
Inputs: targetScope (required), sourceScope.
list_scopesA
List all named scopes in the knowledge base. Shows what hypothetical contexts or reasoning branches exist. The global (unscoped) partition is always present but not listed. Side effects: none (read-only). Auth: requires X-Tenant-ID header; FACT_READ permission when auth is enabled. Rate-limited per principal. Errors: none under normal operation.
Inputs: no named parameters.
merge_scopeA
Merge facts from one scope into another (default: global). Use to commit hypothetical reasoning back into the main knowledge base. Strategy controls conflict handling: SOURCE_WINS overwrites, TARGET_WINS keeps existing, KEEP_BOTH retains both, REJECT aborts on conflict. Side effects: mutates the target scope; may overwrite existing facts depending on strategy (potentially destructive under SOURCE_WINS). Auth: requires X-Tenant-ID header; FACT_WRITE permission when auth is enabled. Rate-limited per principal. Errors: VALIDATION_ERROR on unknown strategy; CONFLICT_ERROR when strategy=REJECT and conflicts are found.
Inputs: sourceScope (required), targetScope, strategy.
predicatesA
Discover the knowledge base schema. Lists all predicates currently stored with arity (argument count), fact count, and whether they have associated rules. Use this before querying to understand what knowledge is available. Side effects: none (read-only). Auth: requires X-Tenant-ID header; FACT_READ permission when auth is enabled. Rate-limited per principal. Errors: none under normal operation.
Inputs: scope.
recallA
Time-travel query: recall what was known at a specific point in time. Returns facts valid at the given timestamp, respecting temporal bounds (validFrom, validUntil, ttl). Useful for debugging agent behavior or reconstructing past state. Side effects: none (read-only). Auth: requires X-Tenant-ID header; FACT_READ permission when auth is enabled. Rate-limited per principal. Errors: VALIDATION_ERROR on bad args or missing timestamp.
Inputs: predicate (required), args (required), timestamp (required), scope.
retract_patternA
Retract all facts matching a pattern in a single call. Use ?-prefixed variables as wildcards to retract multiple facts at once. Returns the count and list of retracted facts. Side effects: DESTRUCTIVE — removes multiple facts and cascades TMS retraction for each removed fact (irreversible). Auth: requires X-Tenant-ID header; FACT_WRITE permission when auth is enabled. Rate-limited per principal. Errors: VALIDATION_ERROR on bad args.
Inputs: predicate (required), args (required), scope.
teachA
Define a logical rule for automatic reasoning. When body conditions hold, head becomes derivable via backward chaining. Use ?-prefixed variables; supports Negation-as-Failure. Example: 'If ?x is human AND NOT god(?x), THEN ?x is mortal'. Side effects: mutates state (additive) — rules remain active until explicitly removed. Auth: requires X-Tenant-ID header; RULE_WRITE permission when auth is enabled. Rate-limited per principal. Errors: VALIDATION_ERROR on malformed rules.
Inputs: head (required), body (required), scope.
tellA
Assert a fact into the knowledge base. Stores knowledge queryable via logical reasoning. Supports TTL expiration, confidence scoring, and configurable conflict resolution. Side effects: mutates state (additive) — stored facts persist until retracted or expired. Auth: requires X-Tenant-ID header for tenant isolation; FACT_WRITE permission when auth is enabled. Rate-limited per principal. Errors: VALIDATION_ERROR on bad args, CONFLICT_ERROR on contradictions when conflictStrategy=REJECT.
Inputs: predicate (required), args (required), scope, negated, +4 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 16 tools
Each tool targets a distinct operation: tell/forget/retract_pattern for facts, teach for rules, ask/aggregate/context/recall for queries, scope management tools, and memory maintenance tools. No two tools have overlapping purposes; clear boundaries between them.
Naming is mixed: some tools use verb_noun (bulk_assert, delete_scope), others are single verbs (ask, forget), and one is a noun (context). While each name is individually clear, the lack of a consistent pattern reduces predictability.
16 tools is slightly above the typical range but justified by the complexity of the knowledge base domain (fact management, rules, queries, scopes, memory). Each tool serves a clear purpose.
The surface covers core CRUD for facts, queries, scopes, schema discovery, and memory management. A minor gap is the absence of a tool to list or remove defined rules, but the overall coverage is strong.
Maintenance
Related MCP Connectors
Cuts coding agent token burn up to 72% continuously via contradiction-free memory & verification.
Agent FinOps Spend Guard, Deterministic Budget Passport, LLM Token Cost Router & VIP Discounts.
Up to 90% fewer tokens: deterministic, declared tool calls, each with a receipt and an audit trail.
Universal memory for AI agents and tools. Save, organize and search context anywhere.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn implementation of persistent memory for Claude using a local knowledge graph, allowing the AI to remember information about users across conversations with customizable storage location.1162JavaScriptMIT

RelayPlaneofficial
AlicenseAqualityDmaintenanceEnables efficient AI workflow orchestration by chaining multi-step LLM operations while keeping intermediate results out of the context window, reducing token usage by 90%+ and supporting multiple AI providers.741 npm1MIT- FlicenseNot gradedqualityDmaintenanceA production-ready reasoning engine that integrates Claude AI with specialized MCP tools for knowledge retrieval, schema validation, and domain-specific rubric evaluation. It enables structured RAG-based analysis across legal, health, and science domains via a RESTful API.-
- AlicenseAqualityDmaintenanceProvides versioned, structured memory for AI agents, allowing them to store facts, detect conflicts, and track knowledge history via a hosted SaaS platform. It enables efficient hierarchical information retrieval and semantic search while keeping token usage constant as memory scales.720 npm8Apache 2.0