claude-mem
Give your coding agents a persistent memory that survives every session.
billion-context est un projet de agents IA open source, créé par ranxianglei (ranxianglei/billion-context sur GitHub). Il compte 7 016 étoiles sur GitHub et 575 forks, il est publié sous la licence MIT et a été mis à jour pour la dernière fois sur GitHub le 12 novembre 2026.
Context compression for long coding sessions — 5x fewer tokens, month-long single sessions, MIT
Install the package from npm into your local prefix.
It sits between your agent and the model API — follow the setup for your agent in the README.
Let the model compress consumed context into layered summaries as the session grows.
The model decides when and what to compress — no hard truncation limit.
About five times fewer tokens per session, with month-long single sessions.
Summaries can be decompressed on demand, and the cache prefix stays intact.
Claude Code, Codex, OpenCode, Pi, Gemini CLI, Kimi, Qwen, Copilot CLI and more.
A published paper and a 1,500-item third-party evaluation back the claims.
Install the package from npm.
npm install -g billion-context --prefix=~/.localOne bili command brings up the proxy and the client together — no config file is touched.
bili claudeA healthy session keeps a 95–97% prefix-cache hit rate; the README FAQ explains the checks.
/acp-cacheTwo 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.
It compresses consumed conversation into layered summaries as a coding session grows, so one session can run for days through a single context window.
About 5x fewer tokens; the third-party benchmark shows 58.3% lower cost than full context on ContextBench.
Claude Code, Codex, OpenCode, Pi, Gemini CLI, Kimi, Qwen Code, Copilot CLI, TRAE, Crush, Zed, Aider and more.
Summaries are high-fidelity and reversible — they can be decompressed on demand.
Yes — MIT, including the paper itself.
Give your coding agents a persistent memory that survives every session.
Drop-in persistent memory infrastructure for AI agents and apps.
Open-source AI-driven development platform: autonomous software agents in a sandbox
Self-managing, unbounded context and long-term memory for coding agents: one session, for life.
AI-native search that indexes code, docs, and PDFs with 40x fewer tokens than grep.
Compression gateway that cuts AI coding agents' token bills up to 85%.
Les autres projets de la catégorie Agents IA avec le plus d'étoiles du catalogue LibreAI — la sélection réaliste d'alternatives si billion-context ne vous convient pas.
A personal AI that really does things — on any OS, with your data staying yours.
Matt Pocock's engineering skills for coding agents — grill the spec first, then build it right, MIT
An agentic skills framework & software development methodology that works.
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
The agent that grows with you — a Python framework for adaptive AI agents.
Projets de la catégorie Agents IA proches dans le catalogue, les plus proches en étoiles de billion-context — continuez à explorer de part et d'autre.
A framework for building agentic apps
Open Multi Agent — a self-hosted TypeScript agent runtime with durable approvals and verifiable run records.
Open-source 7B vision-language-action model and codebase for generalist robot manipulation.
AppAgent — Tencent's multimodal agent that learns smartphone apps by exploration, then operates them.
Product Management skills framework built on battle-tested methods for Claude Code, Cowork, Codex, and AI agents.
A payments protocol for the internet — built on plain HTTP.
Gratuit et ouvert : récupérez le code source, mettez une étoile au dépôt et commencez à créer.