claude-mem
Give your coding agents a persistent memory that survives every session.
billion-context is an open-source ai agents project by ranxianglei (ranxianglei/billion-context on GitHub). It has 7,016 GitHub stars and 575 forks, is released under the MIT license, and was last updated on GitHub on 12 November 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%.
The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if billion-context is not the right fit.
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.
Nearby AI Agents projects in the catalogue, closest in stars to billion-context — keep exploring the shelf either side of it.
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.
Free and open — grab the source, star the repo, and start creating.