Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Multi-agent systems, memory, planning, reasoning loops
| Date | Stars |
|---|---|
| 2026-07-31 | 2842 |
| 2026-08-01 | 2844 |
| 2026-08-03 | 2844 |
| 2026-08-06 | 2844 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
🤝 Show your support - give a ⭐️ if you liked the content ### Agentic AI and Agents Tutorials/Implementations and Notebooks ▶ Building Non-Interactive Agentic Coding Workflows with Moonshot AI’s Kimi CLI, JSONL Streaming, Testing, and Session Memory [Codes](https://github.com/MARKTECHPOST-AI-MEDIA-INC/AI-Agents-Projects-Tutorials/blob/main/Agentic%20AI%20Codes/Kimi_CLI_Advanced_Agentic_Coding_Marktechpost.ipynb) [Tutorial](https://www.marktechpost.com/2026/07/28/building-non-interactive-agentic-coding-workflows-with-moonshot-ais-kimi-cli-jsonl-streaming-testing-and-session-memory/) ▶ Building a Policy-Governed Multi-Agent Financial Research Workflow with Omnigent [Codes](https://github.com/MARKTECHPOST-AI-MEDIA-INC/AI-Agents-Projects-Tutorials/blob/main/Agentic%20AI%20Codes/omnigent_multi_agent_fx_research_Marktechpost.ipynb) [Tutorial](https://www.marktechpost.com/2026/07/30/building-a-policy-governed-multi-agent-financial-research-workflow-with-omnigent/) ▶ Designing Skill-Driven Financial Analysis Agents with Claude, Python, MCP Connectors, and Automated Deliverables [Codes](https://github.com/MARKTECHPOST-AI-MEDIA-INC/AI-Agents-Projects-Tutorials/blob/main/Agentic%20AI%20Codes/claude_financial_services_agentic_workflows_marktechpost.py) [Tutorial](https://www.marktechpost.com/2026/07/27/designing-skill-driven-financial-analysis-agents-with-claude-python-mcp-connectors-and-automated-deliverables/) ▶ Building Self-Evolving AI Agents with OpenSpace Using Skills, MCP, Lineage, and Low-Cost Reuse [Codes](https://github.com/MARKTECHPOST-AI-MEDIA-INC/AI-Agents-Projects-Tutorials/blob/main/Agentic%20AI%20Codes/HKUDS_OpenSpace_Self_Evolving_AI_Agents_Marktechpost.ipynb) [Tutorial](https://www.marktechpost.com/2026/07/25/building-self-evolving-ai-agents-with-openspace-using-skills-mcp-lineage-and-low-cost-reuse/) ▶ Research-Grade EdgeBench Analysis: AI Agent Benchmarking, Leaderboard Analytics, Scaling Laws, and Evaluation Metrics [Codes](https://github.com/MARKTECHPOST-AI-MEDIA-INC/AI-Agents-Projects-Tutorials/blob/main/Data%20Analysis/EdgeBench_Advanced_Analysis_and_Scaling_Laws_Marktechpost.ipynb) [Tutorial](https://www.marktechpost.com/2026/07/22/research-grade-edgebench-analysis-ai-agent-benchmarking-leaderboard-analytics-scaling-laws-and-evaluation-metrics/) ▶ How to Build a T4-Friendly Autonomous Data Science Agent with DeepAnalyze-8B, Sandboxed Code Execution, and Iterative Analysis [Codes](https://github.com/MARKTECHPOST-AI-MEDIA-INC/AI-Agents-Projects-Tutorials/blob/main/AI%20Agents%20Codes/deepanalyze_8b_autonomous_data_science_agent_Marktechpost.ipynb) [Tutorial](https://www.marktechpost.com/2026/07/10/how-to-build-a-t4-friendly-autonomous-data-science-agent-with-deepanalyze-8b-sandboxed-code-execution-and-iterative-analysis/) ▶ Building a Stable Fable 5 Traces Workflow in Colab: Parsing Tool Calls, Auditing Data, and Training Baselines [Codes](https://github.com/MARKTECHPOST-AI-MEDIA-INC/AI-Agents-Projects-Tutorials/blob/main/Agentic%20AI%20Codes/fable5_agent_traces_colab_workflow_marktechpost.py) [Tutorial](https://www.marktechpost.com/2026/06/28/building-a-stable-fable-5-traces-workflow-in-colab-parsing-tool-calls-auditing-data-and-training-baselines/) ▶ Building Supervised Fine-Tuning Data from NVIDIA Open-SWE-Traces: Trajectory Parsing, Patch Analysis, Token Budgets, and Tool-Use Metrics [Codes](https://github.com/MARKTECHPOST-AI-MEDIA-INC/AI-Agents-Projects-Tutorials/blob/main/Agentic%20AI%20Codes/nvidia_open_swe_traces_agent_sft_data_pipeline.py) [Tutorial](https://www.marktechpost.com/2026/06/26/building-supervised-fine-tuning-data-from-nvidia-open-swe-traces-trajectory-parsing-patch-analysis-token-budgets-and-tool-use-metrics/) ▶ Build a Nanobot-Style AI Agent in Google Colab with Tool Calling, Session Memory, Skills, and MCP Servers [Codes](https://github.com/MARKTECHPOST-AI-MEDIA-INC/AI-Agents-Projects-Tutorials/blob/main/AI%20Agents%20Codes/nanobot_style_personal_ai_agent_from_scratch_Marktechpost
Excerpt of 79,524 characters
Read on GitHub
Marktechpost.com · Marktechpost AI · United States
605
421
71
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:bd25d0cdd1596ae6, topic:agentic-ai, topic:agentic-workflow, name:ai agents