Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Bifrost
Bifrost
Busbar
Busbar

Prism-Shadow/model-message-stream-protocol

One interface for 1,000+ LLMs, with zero-code switching and built-in observability. (GPT 6 / Claude 5 / Gemini 4)

#LLM gateway
Visit GitHub
Python
113
15
7 contributors
Apache License 2.0
website
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

Busbar

Control what AI can do before it acts

Momentum

How fast Prism-Shadow/model-message-stream-protocol is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Aug 25 – Oct 21, 2026

Stars +5 in 58 days

012
2

Forks +4 in 58 days

01
1

Merged PRs 69 in 58 days

051015
14

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Aug 25Sep 2Sep 10Sep 18Sep 26Oct 4Oct 12Oct 20
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Tue, Aug 25, 2026+1+03
Wed, Aug 26, 2026+2+12
Thu, Aug 27, 2026+0+00
Fri, Aug 28, 2026+0+00
Sat, Aug 29, 2026+0+00
Sun, Aug 30, 2026+0+00
Mon, Aug 31, 2026+0+00
Tue, Sep 1, 2026+0+00
Wed, Sep 2, 2026+0+03
Thu, Sep 3, 2026+0+11
Fri, Sep 4, 2026+0+04
Sat, Sep 5, 2026+0+10
Sun, Sep 6, 2026+0+00
Mon, Sep 7, 2026+0+00
Tue, Sep 8, 2026+1+00
Wed, Sep 9, 2026+0+06
Thu, Sep 10, 2026+0+00
Fri, Sep 11, 2026+0+03
Sat, Sep 12, 2026+1+06
Sun, Sep 13, 2026+0+00
Mon, Sep 14, 2026+0+04
Tue, Sep 15, 2026+0+01
Wed, Sep 16, 2026+0+00
Thu, Sep 17, 2026+0+00
Fri, Sep 18, 2026+0+10
Sat, Sep 19, 2026+0+00
Sun, Sep 20, 2026+0+00
Mon, Sep 21, 2026+0+00
Tue, Sep 22, 2026+0+00
Wed, Sep 23, 2026+0+00
Thu, Sep 24, 2026+0+00
Fri, Sep 25, 2026+0+00
Sat, Sep 26, 2026+0+00
Sun, Sep 27, 2026+0+00
Mon, Sep 28, 2026+0+00
Tue, Sep 29, 2026+0+01
Wed, Sep 30, 2026+0+014
Thu, Oct 1, 2026+0+07
Fri, Oct 2, 2026+0+00
Sat, Oct 3, 2026+0+00
Sun, Oct 4, 2026+0+01
Mon, Oct 5, 2026+0+00
Tue, Oct 6, 2026+0+00
Wed, Oct 7, 2026+0+00
Thu, Oct 8, 2026+0+00
Fri, Oct 9, 2026+0+05
Sat, Oct 10, 2026+0+00
Sun, Oct 11, 2026+0+00
Mon, Oct 12, 2026+0+00
Tue, Oct 13, 2026+0+00
Wed, Oct 14, 2026+0+05
Thu, Oct 15, 2026+0+00
Fri, Oct 16, 2026+0+00
Sat, Oct 17, 2026+0+00
Sun, Oct 18, 2026+0+00
Mon, Oct 19, 2026+0+03
Tue, Oct 20, 2026+0+00
Wed, Oct 21, 2026+0+00
Total+5+469
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Aug 181 post

    • Meet AgentHub, a better SDK than pi-ai. It is my pick for the agent era. ✅ Python + TypeScript ✅ Built-in observability ✅ Agent skills make it extremely easy to learn Wire in 1,000+ models with zero…

      Read full on X, posted by @code_hiyouga

      @code_hiyouga · x.com

  2. 2 months earlier
  3. Jun 241 post

    • It's hard to define the best skill or prompt, just as it's hard to define the most beautiful painting. We can't optimize them with a single ground truth, only with heuristics, feedback, and a few…

      Read full on X, posted by @code_hiyouga

      @code_hiyouga · x.com

  4. 21 days earlier
  5. Jun 31 post

    • Agent Observability has 4 layers: ①Token-level: CPU/GPU compute & comm. cost per decoded token ②Request-level: network + model latency per API call ③Task-level: LLM / sandbox / tool-call latency per…

      Read full on X, posted by @hiyouga_dev

      @hiyouga_dev · x.com

  6. May 301 post

    • Just released AgentHub v0.3.2. New: Claude Opus 4.8, Gemini Embedding 2, Agent Skills, and interruptible streaming. With OpenAI-compatible mode, it now supports 1000+ models. AgentHub is dirty work,…

      Read full on X, posted by @hiyouga_dev

      @hiyouga_dev · x.com

  7. May 271 post

    • Big update for AgentHub. 7 new models, abortable streaming, and AgentHub Skills. Now Claude Code / Codex can use AgentHub more smoothly to build your first agent app. New models: DeepSeek V4, Gemini…

      Read full on X, posted by @hiyouga_dev

      @hiyouga_dev · x.com

  8. May 261 post

    • I built AgentHub, and I truly believe every AI agent developer needs this tool.

      Read full on X, posted by @hiyouga_dev

      @hiyouga_dev · x.com

  9. 7 days earlier
  10. May 191 post

    • Every agent framework ends up building its own LLM adapter layer. However, this layer is painful to maintain as providers keep changing. AgentHub is built exactly for this, it provides a clean…

      Read full on X, posted by @hiyouga_dev

      @hiyouga_dev · x.com

You might also like

Repositories close to Prism-Shadow/model-message-stream-protocol
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

Busbar

Control what AI can do before it acts

TokenFlux/TokenRouter

Go

tokenrouter is the next generation llm gateway

38454

supermemoryai/llm-bridge

TypeScript

Interoperability between input formats of various LLMs, with observability, error handling, etc. built in.

32635

omnilabs-ai/OmniRouter

Python
9325

theopenco/llmgateway

TypeScript

Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.

1.7k201

bestruirui/octopus

TypeScript

One Hub All LLMs For You | 为个人打造的 LLM API 聚合网关

2.7k427

supercorp-ai/supercompat

TypeScript

AI compatibility without compromises.

10013

inference-gateway/inference-gateway

Go

An open-source, cloud-native, high-performance gateway unifying multiple LLM providers, from local solutions like Ollama to major cloud providers such as OpenAI, Groq, Cohere, Anthropic, Cloudflare and DeepSeek.

21775

BerriAI/litellm

Python

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

61.7k13.1k

mozilla-ai/any-llm

Python

Communicate with an LLM provider using a single interface

2.2k267