RepoAlerts
SponsorGet alerts

ranxianglei/billion-context

Get alerts like thisView on GitHubShare on X

Can I trust it?

Be careful with this one.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change today.

  • Licence Careful

    No licence: legally you can't reuse the code, unless the README says otherwise.

Quick checks from public data. They help, but they are no guarantee.

What it is

A context-compression proxy that sits between coding agents and model APIs, rewriting Anthropic and OpenAI streams. It injects tools so the model can compress conversation ranges into summaries, decompress them on demand, and search context, aiming to keep long sessions within…

Who it's for

Developers running long coding-agent sessions with Claude Code, Codex, Cursor, or similar clients who want to reduce token usage

How to use it

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up ranxianglei/billion-context in my project. Follow its README: https://github.com/ranxianglei/billion-context. Explain each step and check it is safe before running anything.

Read the README

Star curve

2.1KFrom 145 to 2,108 stars between 14 Sept 2026 and 20 Oct 2026.

Alternatives

Similar projects named in its profile. Each link searches the directory.

Get alerts for repos like this

We'll email you when something in AI agents starts rising. Free, once a week, only what matches.

18,265 GitHub repos watched and ranked every hour. Figures as of 20 October 2026.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![ranxianglei/billion-context on RepoAlerts](https://repoalerts.com/badge/ranxianglei/billion-context.svg)](https://repoalerts.com/repo/ranxianglei/billion-context?ref=badge)
Share on X
  • mksglu/context-mode

    Context Mode is an MCP server and hook set for AI coding agents that keeps raw tool output out of the context window by running it in a sandbox, and stores session events in SQLite FTS5 for retrieval

    AI agentsTypeScript · 31,314 stars · +3,054 this week · 240 days old

  • thesysdev/openui

    A TypeScript framework for generative UI in which models stream a compact language (OpenUI Lang) that is rendered as live interface components. Component libraries generate system prompts, with runtim

    Web & UITypeScript · 12,583 stars · +1,730 this week · 687 days old

  • ThinkWatchProject/ThinkWatch-Lite

    Local gateway that sits between AI clients such as Claude Code and Codex and their upstreams. It lets upstreams and models be switched in the gateway alone, records each request with its cost and rout

    Dev infrastructureTypeScript · 803 stars · +543 this week · 38 days old

  • HazyResearch/ncm

    Research code for Next-Concept Modeling, a two-stage framework for parallel text generation. A multiscale residual VQ tokenizer encodes a sequence as a hierarchy of discrete codes, and a transformer p

    Models & inferencePython · 500 stars · +497 this week · 10 days old

  • bealesh/neckbeard

    Claude Code plugin that reads an app's repo, asks open questions, and maps the answers onto a versioned catalog of OpenTofu modules to scaffold cloud infrastructure for AWS, GCP, or Azure. It estimate

    AI agentsGo · 261 stars · +255 this week · 42 days old · HN 78 pts

  • fudan-generative-vision/Remory

    Adds learned residual memory to an agent's compaction summary. The memory is encoded from the conversation history, conditioned on the summary, and appended after it so a frozen LLM can continue work

    AI agentsPython · 325 stars · +222 this week · 14 days old