LibreAI / KI-Agenten / billion-context
// agents · ranxianglei/billion-context

billion-context

billion-context ist ein Open-Source-Projekt aus der Kategorie KI-Agenten von ranxianglei (ranxianglei/billion-context auf GitHub). Es hat 7.016 Sterne auf GitHub und 575 Forks, wird unter der Lizenz MIT veröffentlicht und wurde zuletzt am 12. November 2026 auf GitHub aktualisiert.

Context compression for long coding sessions — 5x fewer tokens, month-long single sessions, MIT

★ 7,0 Tsd. Sterne⑂ 575 ForksMITaktualisiert Nov 2026
▦ Visual — das README dieses Projekts enthält keinen einbettbaren Screenshot,
darum hier ein Platzhalter. Die Anleitung unten ist trotzdem vollständig.
// projektdaten

Projektdaten

GitHub-Sterne
7.016
Forks
575
Lizenz
MIT
Zuletzt auf GitHub aktualisiert
12. November 2026
Kategorie
KI-Agenten
Eintragstyp
Vollständige Installationsanleitung
Offizielle Website
npm package
// so funktioniert es

So funktioniert es

  1. Install it globally

    Install the package from npm into your local prefix.

  2. Point your agent at it

    It sits between your agent and the model API — follow the setup for your agent in the README.

  3. Work a long session

    Let the model compress consumed context into layered summaries as the session grows.

// funktionen

Warum es so beliebt ist

Model-driven compression

The model decides when and what to compress — no hard truncation limit.

5x fewer tokens

About five times fewer tokens per session, with month-long single sessions.

Reversible, cache-friendly

Summaries can be decompressed on demand, and the cache prefix stays intact.

Works with any agent

Claude Code, Codex, OpenCode, Pi, Gemini CLI, Kimi, Qwen, Copilot CLI and more.

Benchmarked in the open

A published paper and a 1,500-item third-party evaluation back the claims.

// selbst ausführen

Führe es selbst aus

  1. Step 1 — Install globally

    Install the package from npm.

    npm install -g billion-context --prefix=~/.local
  2. Step 2 — Launch your agent through it

    One bili command brings up the proxy and the client together — no config file is touched.

    bili claude
  3. Step 3 — Check cache health

    A healthy session keeps a 95–97% prefix-cache hit rate; the README FAQ explains the checks.

    /acp-cache
// anwendungsfälle

Was du damit bauen kannst

  • Keep a coding session alive for days without losing context
  • Cut token costs on long agent runs
  • Run marathon refactors in a single session
  • Compare compression against full context with the published benchmarks

Two more from the same shelf: claude-mem — Give your coding agents a persistent memory that, and mem0 — Drop-in persistent memory infrastructure for AI. Browse every AI Agents tool in the catalogue to compare the category. Before running a model locally, check how much VRAM you need for local LLMs — model size has to match your hardware.

// häufige fragen

Häufige Fragen

What does billion-context do?

It compresses consumed conversation into layered summaries as a coding session grows, so one session can run for days through a single context window.

How much does it save?

About 5x fewer tokens; the third-party benchmark shows 58.3% lower cost than full context on ContextBench.

Which agents does it work with?

Claude Code, Codex, OpenCode, Pi, Gemini CLI, Kimi, Qwen Code, Copilot CLI, TRAE, Crush, Zed, Aider and more.

Is compression lossy?

Summaries are high-fidelity and reversible — they can be decompressed on demand.

Is it free?

Yes — MIT, including the paper itself.

// weiter entdecken

Ähnliche Tools

KI-Agenten

claude-mem

Give your coding agents a persistent memory that survives every session.

★ 97,9 Tsd. SterneApache-2.0
Anleitung ansehen →
KI-Agenten

mem0

Drop-in persistent memory infrastructure for AI agents and apps.

★ 66,8 Tsd. SterneApache-2.0
Anleitung ansehen →
KI-Agenten

OpenHands

Open-source AI-driven development platform: autonomous software agents in a sandbox

★ 90,3 Tsd. SterneMIT
Anleitung ansehen →
KI-Agenten

magic-context

Self-managing, unbounded context and long-term memory for coding agents: one session, for life.

★ 2,3 Tsd. SterneMIT
Anleitung ansehen →
KI-Agenten

xerj

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

★ 2,6 Tsd. SterneApache-2.0
Anleitung ansehen →
KI-Agenten

paritok-4b-v1

Compression gateway that cuts AI coding agents' token bills up to 85%.

★ 1,5 Tsd. SterneApache-2.0
Anleitung ansehen →
// alternativen

Alternativen im Bereich KI-Agenten

Die anderen Projekte der Kategorie KI-Agenten mit den meisten Sternen im LibreAI-Katalog — die realistische Auswahl, falls billion-context nicht das Richtige ist.

  • openclaw★ 391,6 Tsd.

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

  • Skills For Real Engineers★ 322,7 Tsd.

    Matt Pocock's engineering skills for coding agents — grill the spec first, then build it right, MIT

  • superpowers★ 294,9 Tsd.

    An agentic skills framework & software development methodology that works.

  • ECC★ 275,2 Tsd.

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

  • hermes-agent★ 252,0 Tsd.

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

// mehr in agents

Mehr in KI-Agenten

Verwandte Projekte der Kategorie KI-Agenten im Katalog, die billion-context bei den Sternen am nächsten stehen — zum Weiterstöbern auf beiden Seiten.

  • agent-native★ 7,0 Tsd.

    A framework for building agentic apps

  • open-multi-agent★ 7,0 Tsd.

    Open Multi Agent — a self-hosted TypeScript agent runtime with durable approvals and verifiable run records.

  • openvla★ 7,1 Tsd.

    Open-source 7B vision-language-action model and codebase for generalist robot manipulation.

  • AppAgent★ 6,9 Tsd.

    AppAgent — Tencent's multimodal agent that learns smartphone apps by exploration, then operates them.

  • Product-Manager-Skills★ 7,2 Tsd.

    Product Management skills framework built on battle-tested methods for Claude Code, Cowork, Codex, and AI agents.

  • x402★ 6,7 Tsd.

    A payments protocol for the internet — built on plain HTTP.

Hol dir billion-context

Kostenlos und offen — hol dir den Quellcode, gib dem Repository einen Stern und leg los.