Data / Repositories / LLM agents / Python
Python LLM agents repositories on GitHub: 11 ranked by stars
11 public Python repositories tagged LLM agents are on GitHub, with 57,812 stars between them; 10 had a push in the last 30 days. The most starred: HKUDS/nanobot (49,026), IBM/mcp-context-forge (4,629), IBM/AssetOpsBench (2,355).
SpecStream is the live web data engine for teams and agents. It reads open-source repositories on GitHub and keeps what it reads, and this page groups that reading by topic. Ask for the repositories you track by topic, language, license or activity, and new ones and changes arrive in your sheet, CRM, Slack or agent.
Every repository, most starred first
| Repository | What it is | Stars | Forks | License | Last push | Read |
|---|---|---|---|---|---|---|
| HKUDS/nanobot | Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps | 49,026 | 8,629 | MIT | Oct 14 | Oct 14 |
| IBM/mcp-context-forge | An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management.… | 4,629 | 922 | Apache-2.0 | Oct 14 | Oct 14 |
| IBM/AssetOpsBench | AssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and… | 2,355 | 338 | Apache-2.0 | Oct 14 | Oct 14 |
| RyanAlberts/best-of-Agent-Harnesses | Ranked list of 167 AI agent harnesses, plus templates, playbooks, MCP, and learning resources. Rescored weekly. | 1,131 | 66 | CC-BY-SA-4.0 | Oct 9 | Oct 11 |
| scaleapi/agentenv-framework | Creating realistic RL environments requires collaboration between researchers, engineers, and domain experts across many dimensions: artifacts, environments tools, dynamism of the… | 312 | 28 | Apache-2.0 | Oct 15 | Oct 15 |
| fudan-generative-vision/Remory | Remory: Learning Residual Memory for Context Compaction | 160 | 9 | MIT | Oct 15 | Oct 15 |
| GhalebDweikat/winnow | A calibrated context sieve for Claude Code: every tool result is judged by a System One model before it enters context. | 110 | 14 | MIT | Oct 6 | Oct 15 |
| ChaoYue0307/awesome-graph-engineering | Engineer the organization, not just the agent. 601 curated resources · 9 design layers · 11 sections · 279 papers & preprints — a field guide, CC0 open dataset, and interactive… | 42 | 7 | CC0-1.0 | Sep 26 | Oct 14 |
| eunsanMountain/atlassian-skills | Token-efficient CLI for Atlassian Server/DC (Jira, Confluence, Bitbucket) — drop-in alternative to mcp-atlassian for LLM agents. Compact output, lossless XHTML<->Markdown… | 25 | 9 | MIT | Aug 4 | Oct 14 |
| Htunn/aiops-orchestrator | A production-ready, multi-channel AI agent for AIOps, Kubernetes management, and automated remediation — built on FastAPI with support for GitHub Models and Google Gemini LLM… | 16 | 3 | MIT | Oct 3 | Oct 14 |
| nicotem/exegete | Exegete: full feature, qualitative data analysis through a conversation with your AI assistant, compatible with QualCoder projects. Runs on your computer as an MCP server… | 6 | 0 | LGPL-3.0 | Oct 14 | Oct 14 |
Other languages
Related topics
- MCP 14
- Model Context Protocol 10
- AI agents 9
- LLM 6
- Python 6
- Agentic AI 6
- AI 5
- Awesome list 5
- Claude Code 5
- AI tools 4
- MCP server 4
- Agent framework 3
Read from GitHub by SpecStream between October 11, 2026 and October 15, 2026; each row shows the day its repository was read. Stars and pushes change every day, and the GitHub page is the current one. Forks and archived repositories are left out.