LibreAI / Agentes de IA / agentic-context-engine
// agents · kayba-ai/agentic-context-engine

agentic-context-engine

agentic-context-engine es un proyecto de agentes de IA de código abierto de kayba-ai (kayba-ai/agentic-context-engine en GitHub). Tiene 2.586 estrellas en GitHub y 312 bifurcaciones, se publica bajo la licencia Apache-2.0 y se actualizó por última vez en GitHub el 24 de septiembre de 2026.

Make your agents learn from experience with a dedicated context engine.

💎 Joya oculta★ 2,6k estrellas⑂ 312 bifurcacionesApache-2.0actualizado sep 2026
▦ visual: el README de este proyecto no incluye ninguna captura incrustable,
así que aquí va un marcador. La guía de abajo está completa de todos modos.
// datos del proyecto

Datos del proyecto

Estrellas en GitHub
2.586
Bifurcaciones
312
Licencia
Apache-2.0
Última actualización en GitHub
24 de septiembre de 2026
Categoría
Agentes de IA
Tipo de ficha
Joya oculta: una página más breve para un proyecto menos conocido
Sitio oficial
Official site
// cómo funciona

Cómo funciona

  1. Connect your agent

    Hook the engine into your agent loop.

  2. Capture experience

    Runs are recorded as learnable context.

  3. Distill lessons

    The engine extracts what worked.

  4. Improve future runs

    Agents start smarter next time.

// características

Por qué gusta tanto

Experience learning

Agents improve from past runs.

Context distillation

Lessons extracted automatically.

Python native

Fits existing agent stacks.

Hosted option

A managed service is available.

Memory focused

Built for long-horizon tasks.

Framework friendly

Works with your agent code.

Advertisement
// ejecútalo

Ejecútalo tú mismo

  1. Step 1 — Clone the repo

    Download the source and move into the project folder.

    git clone https://github.com/kayba-ai/agentic-context-engine.git
    cd agentic-context-engine
  2. Step 2 — Check the README

    Every project documents its own setup; start with install requirements.

    cat README.md | head -60
  3. Step 3 — Run it

    Follow the project’s launch command — Docker, pip, npm, or a binary release.

    # see README for the exact launch command
// casos de uso

Qué puedes crear

  • Give agents persistent learning.
  • Improve agent quality over time.
  • Capture institutional agent knowledge.
  • Reduce repeated mistakes.
Advertisement
// preguntas frecuentes

Preguntas frecuentes

Who maintains it?

It is an open-source project at kayba-ai/agentic-context-engine with 312 forks.

Is it free for commercial use?

The code is Apache-2.0; the hosted version has its own pricing.

How is this different from vector memory?

It focuses on learning from experience, not just storing facts.

Can I self-host it?

Yes. The engine is open source.

Which agent frameworks work?

It is designed to hook into your existing agent loop.

// sigue explorando

Herramientas similares

Agentes de IA

mempalace

The best-benchmarked open-source AI memory system. And it's free.

★ 59,4k estrellasMIT
Ver la guía →
Agentes de IA

TencentDB-Agent-Memory

TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill,…

★ 27,7k estrellasUnknown
Ver la guía →
Agentes de IA

agentops

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI …

★ 5,9k estrellasMIT
Ver la guía →
Agentes de IA

BrowserOS

Open-source agentic browser your AI agents drive with your logins, plus an AI browser for humans.

★ 13,8k estrellasAGPL-3.0
Ver la guía →
Agentes de IA

evolver

A GEP-powered self-evolving engine for AI agents — auditable evolution with Genes, Capsules and Events.

★ 9,1k estrellasGPL-3.0
Ver la guía →
Agentes de IA

honcho

Honcho — Plastic Labs' memory library for stateful agents that learn about their users over time.

★ 7,5k estrellasAGPL-3.0
Ver la guía →
// alternativas

Alternativas en Agentes de IA

Los demás proyectos de Agentes de IA con más estrellas del catálogo de LibreAI: la lista realista de alternativas si agentic-context-engine no es lo que buscas.

  • openclaw★ 391,6k

    A personal AI that really does things — on any OS, with your data staying yours.

  • superpowers★ 294,9k

    An agentic skills framework & software development methodology that works.

  • ECC★ 275,2k

    Agent harness optimization system with skills, memory and security for Claude Code, Codex and more

  • hermes-agent★ 252,0k

    The agent that grows with you — a Python framework for adaptive AI agents.

  • deepseek-harness★ 245,5k

    DeepSeek's plugin-based agent harness where everything is a plugin.

// más en agents

Más en Agentes de IA

Proyectos de Agentes de IA cercanos en el catálogo, los más próximos en estrellas a agentic-context-engine: sigue explorando a ambos lados.

  • agentfield★ 2,6k

    Build, run, and scale AI agents like APIs and microservices.

  • griptape★ 2,6k

    Modular Python framework for AI agents and workflows with tools and memory.

  • Data-Analysis-Agent★ 2,6k

    Chat with your data: an LLM agent that builds charts and business insights.

  • deepagents-in-action★ 2,6k

    Chinese guide to building production-grade AI agents with LangChain and LangGraph.

  • xerj★ 2,6k

    AI-native search that indexes code, docs, and PDFs with 40x fewer tokens than grep.

  • MiroFish-Offline★ 2,6k

    Offline multi-agent simulation and prediction engine: Neo4j plus Ollama, local.

Consigue agentic-context-engine

Gratis y abierto: consigue el código fuente, dale una estrella al repositorio y empieza a crear.