Spotted in the agentic-ai patch, a young specimen rooted in Python. Fresh from the seed bed.
In the maintainer's words The most complete open-source, self-hosted Agentic Trading OS—AI research, Python strategies, factor discovery, backtesting, optimization, paper/live multi-asset execution, risk controls, monitoring, MCP, and multi-tenant SaaS in one auditable stack.
3 of your topics (ai-agents, mcp, self-hosted)
merged 26 outside PRs in 90 days
~1278 stars a month (new, 11 months ago, top 31% in self-hosted)
Found in the devtools patch: a young TypeScript specimen. A seedling, new this season.
In the maintainer's words Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.
4 of your topics (ai-agents, claude-code, devtools, mcp)
merged 22 outside PRs in 90 days
~2160 stars a month (new, 5 months ago, top 6% in devtools)
A young TypeScript specimen, spotted in the self-hosted patch. Barely out of the soil.
In the maintainer's words Coolest app to use agents, local, multi provider and open source grok bot alternative. Build custom worlds for your claude code and codex like agents
3 of your topics (ai-agents, claude-code, self-hosted)
~1684 stars a month (new, 6 months ago, top 25% in self-hosted)
A young TypeScript specimen, spotted in the agentic-ai patch. Barely out of the soil.
In the maintainer's words Open source device layer for AI coding agents: a CLI, MCP server, and typed Node.js API to control mobile, web, TV, and desktop apps on devices and simulators, locally or in the cloud.
3 of your topics (ai-agents, flutter, mcp)
~558 stars a month (new, 10 months ago, top 11% in flutter)
Found in the agentic-ai patch: a young Python specimen. Fresh from the seed bed.
In the maintainer's words Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
2 of your topics (claude-code, mcp)
merged 36 outside PRs in 90 days
~3326 stars a month (new, 8 months ago, top 38% in mcp)
A young find from in the self-hosted patch, rooted in Python. Fresh from the seed bed.
In the maintainer's words RocketRide is an open source AI meta-harness with the only enterprise-grade runtime built on C++. Build, test and publish durable agents that scale in production.
3 of your topics (ai-agents, mcp, self-hosted)
~2136 stars a month (new, 9 months ago, top 18% in self-hosted)
Found in the cybersecurity patch: a young Python specimen. A seedling, new this season.
In the maintainer's words Open-source AI Security Operations Center: alert fusion, LLM-agent triage, MITRE ATT&CK investigation, and a replayable decision ledger for every agent step. Self-hostable, runs with no API keys, MIT licensed. Ships an MCP server for Claude, Cursor and Continue.
2 of your topics (mcp, self-hosted)
~1054 stars a month (new, 7 months ago, top 36% in self-hosted)
Young HTML growth, turned up in the claude-code patch. Fresh from the seed bed.
In the maintainer's words 45+ tips for getting the most out of Claude Code, from basics to advanced - includes a custom status line script and Claude Code running itself in a container. Also includes the dx plugin: skills for everyday dev workflows.
2 of your topics (claude-code, cli)
merged 5 outside PRs in 90 days
answered 3 of 4 recent issues
~869 stars a month (new, 12 months ago, top 64% in cli)
Spotted in the agentic-ai patch, a young specimen rooted in Python. A seedling, new this season.
In the maintainer's words Open-source agentic AI operating layer for hospital operations — multi-agent orchestration over FHIR-connected HIS data, built on LangGraph and Temporal.
2 of your topics (ai-agents, fhir)
~5 stars a month (new, 4 months ago, top 25% in fhir)
Young TypeScript growth, turned up in the database patch. Barely out of the soil.
In the maintainer's words Open-source database & workspace for AI agents — structured data, durable knowledge, reusable skills, runnable apps, and human review on the writes that matter. Local-first and self-hostable.
4 of your topics (ai-agents, database, mcp, self-hosted)
~186 stars a month (new, 5 months ago, top 37% in database)
Young Python growth, turned up in the tui patch. Barely out of the soil.
In the maintainer's words 🧩 FrontierAgent, our agent framework, open-sourced alongside it — native command-line TUI, ReAct and Agent Team modes, one command on macOS and Linux, no preinstall, no hard Docker dependency.
~1815 stars a month (new, 3 months ago, top 16% in tui)
A young find from in the typescript patch, rooted in TypeScript. Fresh from the seed bed.
In the maintainer's words Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views.
~8127 stars a month (new, 4 months ago, top 2% in typescript)
Young Python growth, turned up in the agentic-ai patch. Fresh from the seed bed.
In the maintainer's words World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video produ…
~10419 stars a month (new, 8 months ago, top 3% in agentic-ai)
Young TypeScript growth, turned up in the docker-compose patch. Fresh from the seed bed.
In the maintainer's words Open-source, self-hosted Slack alternative where your team and AI agents work together in channels and DMs. Agents run on Claude, ChatGPT/Codex, Gemini or Grok, with MCP tools, their own computer and…
~4633 stars a month (new, 12d ago, top 3% in docker-compose)
Young Python growth, turned up in the cli patch. Fresh from the seed bed.
In the maintainer's words Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode,…
~616 stars a month (new, 10 months ago, top 27% in developer-tools)
Young TypeScript growth, turned up in the cli patch. Fresh from the seed bed.
In the maintainer's words 🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — all AI remember the same you. Now supports Claude Code, Codex,…
~526 stars a month (new, 4 months ago, top 27% in tui)
Spotted in the llm patch, a young specimen rooted in Jupyter Notebook. Fresh from the seed bed.
In the maintainer's words 🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
~658 stars a month (new, 8 months ago, top 10% in pytorch)
Spotted in the agentic-ai patch, a young specimen rooted in Python. A seedling, new this season.
In the maintainer's words Agentic AI security scanner that hunts exploitable vulnerabilities like an adversary, proves them with executable PoCs, and fixes them test-first. A maintained fork of Capital One's VulnHunter, rebui…
~419 stars a month (new, 59d ago, top 15% in vulnerability-scanner)
Found in the ai-agents patch: a young Python specimen. A seedling, new this season.
In the maintainer's words Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.
~459 stars a month (new, 9 months ago, top 30% in rag)
Found in the llm patch: a young JavaScript specimen. Barely out of the soil.
In the maintainer's words Desktop creatures with an AI sidekick that lives on your screen. Talk to it, it remembers what you said you'd do, reminds you and points at things. Your choice of AI. Mac and Windows.
~515 stars a month (new, 23d ago, top 29% in rust)
A young find from in the agentic-ai patch, rooted in Python. Fresh from the seed bed.
In the maintainer's words Open-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens PRs that fix what i…
~318 stars a month (new, 11 months ago, top 31% in cybersecurity)
Spotted in the kubernetes patch, a young specimen rooted in Python. Fresh from the seed bed.
In the maintainer's words Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure.
~230 stars a month (new, 8 months ago, top 36% in self-hosted)
A young find from in the agentic-ai patch, rooted in Python. A seedling, new this season.
In the maintainer's words Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opi…
~130 stars a month (new, 5 months ago, top 39% in computer-vision)
Young TypeScript growth, turned up in the ai-agents patch. A seedling, new this season.
In the maintainer's words AI coding dream team of agents for VS Code. Claude Code + openai Codex collaborate in brainstorm mode, debate solutions, and synthesize the best approach for your code.
~98 stars a month (new, 12 months ago, top 30% in vscode-extension)
A young find from in the ai-agents patch, of no fixed habitat. A seedling, new this season.
In the maintainer's words Free interactive tools for data scientists to learn MLOps, ML system design and agentic analytics: a production ML system map, ML project structure, data drift simulator, agentic analytics system map…
~497 stars a month (new, 18d ago, top 18% in data-science)
A young TypeScript specimen, spotted in the agentic-ai patch. A seedling, new this season.
In the maintainer's words React design system for agentic interfaces. Every free BoardUI component as source, with a working AI chat app on your own model key as the homepage.
~465 stars a month (new, 3 months ago, top 20% in tailwindcss)
Spotted in the monitoring patch, a young specimen rooted in Python. Barely out of the soil.
In the maintainer's words open source agent engineering platform: traces, evals, and metrics to debug and improve your AI agents. Integrates with LangGraph, CrewAI, Claude Agent SDK, and more.
~77 stars a month (new, 11 months ago, top 53% in monitoring)
Spotted in the mcp patch, a young specimen rooted in JavaScript. A seedling, new this season.
In the maintainer's words The independent security agent for AI-written software. Finds issues, investigates whether they are real, and shows you the evidence. Deterministic core, no API key needed, JSON and SARIF output.
~90 stars a month (new, 10 months ago, top 42% in devsecops)
A young find from in the ios patch, rooted in TypeScript. Barely out of the soil.
In the maintainer's words A collection of Agent Skills Standard and Best Practice for Programming Languages, Frameworks that help our AI Agent follow best practies on frameworks and programming laguages
~57 stars a month (new, 10 months ago, top 58% in golang)
Found in the data-science patch: a young Dart specimen. Barely out of the soil.
In the maintainer's words PocketStrike is a privacy-first mobile AI workstation. It combines zero-cloud native on-device GGUF inference (ARM NEON accelerated) │ with frontier cloud LLMs, multi-step ReAct agent tools, Model Co…
~61 stars a month (new, 3 months ago, top 49% in data-science)
Young Rust growth, turned up in the ai-agents patch. Fresh from the seed bed.
In the maintainer's words Local, LLM-free memory for AI agents. A single offline Rust binary — deterministic and auditable — that learns from use, forgets the irrelevant, and strengthens what matters. No cloud, no API keys.
pushed 4d ago
~28 stars a month (new, 12 months ago, top 79% in rust)
Young Python growth, turned up in the agentic-ai patch. Barely out of the soil.
In the maintainer's words 🤖 AI Agent-driven Kaggle competition workflow. Battle-tested patterns for score stabilization, submission troubleshooting, kernel workflows, and spec-driven development.
~29 stars a month (new, 7 months ago, top 72% in data-science)
Spotted in the ai-agents patch, a young specimen rooted in TypeScript. Barely out of the soil.
In the maintainer's words Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
pushed today
~25 stars a month (new, 9 months ago, top 85% in devsecops)