# microsoft/agent-framework

> Microsoft's open multi-language framework for building, orchestrating and deploying production-grade AI agents and multi-agent workflows in Python, .NET and Go. Supports graph patterns, middleware, observability and multiple LLM providers.

- Magnitude: 2.4 out of 10 — Steady
- Stars: 14,004 total · +1 star measured 2026-10-08, 10:59–11:51 UTC, ≈ 8 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: Python · License: MIT · Created: 2025-04-28 · Last push: 2026-10-08
- GitHub: https://github.com/microsoft/agent-framework · Homepage: https://aka.ms/agent-framework · Page: https://gitnova.dev/en/r/microsoft/agent-framework

## Useful for

- Build a multi-agent workflow with sequential or concurrent orchestration in Python
- Connect an agent to Azure OpenAI or Microsoft Foundry via a ready client
- Add OpenTelemetry tracing and human-in-the-loop to an existing agent

## Why it’s here

- Star-counter measurements on 2026-10-08 (UTC), 10:59–11:51: 14003 → 14004 stars (+1). This is the change over that interval.
- Estimated end-of-day forecast: about +8 stars, using observed gains and the previous day.
- GitHub Trending Python today: #9, +24 stars.
- About 9 forks a day — people are taking the code.
- Recent forks include notable developers: @victorpreston (1,351 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 2,444
- Issues and pull requests: 8,739
- Watchers: 110
- Average over the last week: 15 per day
- Usual pace: 22 per day
- Stars in the last hour (measured): 4
- Latest release: python-1.21.0 (2026-10-08)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-09 … 2026-10-08: 35, 17, 26, 14, 11, 17, 18, 15, 19, 19, 14, 48, 60, 30, 25, 15, 20, 16, 15, 22, 22, 18, 19, 13, 16, 11, 12, 19, 27, 1

## Spotted in now

- GitHub Trending Python today: #9, +24 stars

## More in this category

1. **morluto/rea** — 9.3 · Breakout · AI agents · TypeScript · +4,279 stars measured 2026-10-08, 00:01–11:45 UTC, ≈ 8,132 by evening
   A reverse-engineering tool that lets AI agents inspect apps and native binaries: it connects agents to Hopper or Ghidra via MCP and CLI, helping explain how a feature works and rebuild it in your own project.
   Full card: https://gitnova.dev/en/r/morluto/rea.md
2. **docker/docker-agent** — 8.0 · Breakout · AI agents · Go · +362 stars measured 2026-10-08, 00:01–11:45 UTC, ≈ 673 by evening
   Docker CLI plugin for building and running AI agents from a declarative YAML config with tools, MCP servers, and multi-agent orchestration. Lets you assemble agent teams without writing code and share them via OCI registry.
   Full card: https://gitnova.dev/en/r/docker/docker-agent.md
3. **lexmount/moli** — 7.5 · Breakout · AI agents · Rust · +965 stars measured 2026-10-08, 00:01–11:45 UTC, ≈ 1,795 by evening
   Moli is a headless browser written in Rust for AI agents, combining a full browser runtime with on-demand layout and rendering to keep resource use low. It fetches and extracts web pages, searches the web, and automates browser tasks via…
   Full card: https://gitnova.dev/en/r/lexmount/moli.md
4. **thedotmack/claude-mem** — 7.0 · Breakout · AI agents · TypeScript · +354 stars measured 2026-10-08, 00:01–11:45 UTC, ≈ 691 by evening
   Persistent memory system for Claude Code and other agents: it captures agent actions via lifecycle hooks, compresses them into semantic summaries, and injects relevant context into future sessions.
   Full card: https://gitnova.dev/en/r/thedotmack/claude-mem.md
5. **nano-muse/nanoMuse** — 6.7 · Early signal · AI agents · Swift · +97 stars measured 2026-10-08, 00:02–11:46 UTC, ≈ 194 by evening
   Open-source personal AI agent for all your devices: performs tasks via shell, browser, MCP and screen control, remembers you and asks permission before irreversible actions. Runs on Android, iOS, desktop and browser, can be self-hosted.
   Full card: https://gitnova.dev/en/r/nano-muse/nanoMuse.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-08 12:00 UTC, updated every 30 minutes.