Trending AI repositories
Tracked daily across the agentic ecosystem. Velocity is computed from our own snapshot history — collecting the first week of data now; repos are linked to the startups behind them.
VS Code Extension for the Pi Agent.
Forge a working, testable, publishable MCP server in 30s. TypeScript or Python, with example tools, the Inspector and tests included.
Durable, file-based long-term memory for AI agents. Five-package plugin family: SDK, CLI, MCP server, Hermes adapter, and a LangGraph BaseStore. No vector database, no embeddings.
Stop re-explaining yourself
Local-first MCP gateway. One port for every tool and every AI client: lazy discovery (~90% token savings), tool integrity + quarantine, secrets in the OS keychain.
Dryforge : New generation of harness engineering - Claude Code & Codex Plugin.
Real-time gamified dashboard for monitoring Claude Code and Codex AI agents in a medieval fantasy setting
Native macOS app for Pi coding-agent. Browse, resume sessions, and run Pi terminal tabs locally or over SSH.
Coding agent orchestration for engineering teams — shipped as a spec plus a working reference implementation.
Control different agents with agents. Free, local, workspace for AI agents. Let one agent (Claude Code, Codex, Hermes, DeepSeek, Kimi, ...) spawn and drive others over MCP. No API keys, no changes to your Agent.md or Claude.md. TUI, Web UI, CLI, MCP in one package.
An AI workforce platform: role-specialized agents with multi-provider LLM, MCP, tasks, and a web + CLI UI. You're in charge.
Local-first AI daemon for Logseq OG: background semantic indexing, link hygiene, and agent-ready CLI/MCP — edits Markdown on disk (no cloud, no Logseq API). Karpathy LLM-Wiki inspired.
All of your agents, shells, and TUIs in one durable terminal workspace
Turn Claude Code into an equity-research agent: 24 analysis skills (Anthropic's open-source bundle + community), a single data MCP, and a personalization layer for investors at any level.
AI framework for Ruby/Rails developers
Continuum — the agent runtime by ShyftLabs. Build, orchestrate, ship.
A curated list of papers and resources based on the survey "Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspective"
Self-hosted AI workspace where chat becomes visual workflows, multi-agent operations, and reviewable automations. Local memory; local or cloud models
The factory for custom internal software, purpose-built for human2agent work.
Train your AI coders the way you'd train a vine — discover your codebase's actual patterns, then encode them as Claude Code rules, skills, agents, hooks, and a guided pipeline so generated code lands inside your conventions on the first try, not the fifth.
A modular UX, design, and product optimisation system for turning AI-built interfaces into production-grade apps, turning proven principles into enforceable constraints that reduce friction, build trust, and drive action. Works with Claude, Codex, Cursor + all other agentic AI models.
Visualize Pydantic AI agent workflows from Logfire traces as an interactive HTML diagram — tools, nested sub-agents, tokens and exact cost.
Isolated Linux desktop workspaces for AI agents — a hidden, agent-owned desktop and browser over MCP, so an agent can do GUI and web work without touching your real desktop.
Real-time cost observability for Model Context Protocol (MCP) tool calls. Wraps any MCP server, attributes spend per tool/project/customer. Free tier 25K calls/mo. EU-hosted
Skill to generate the knowledge vault for projects using the Ralph loop
Kubernetes-native sandbox platform to run AI agents, coding assistants and harnesses.
macOS 26+ browser CLI for agents: persistent sessions, compact JSON, screenshots, clicks/forms, JS eval, and live preview in under 2 MB.
Composable data security plane for Model Context Protocol. Pluggable layers — collect, analyze, guard — across 50+ enterprise providers. Open architecture.
Most AI agents forget you the moment the tab closes. Constellation Engine gives them a hippocampus — a living star map with spreading activation, Hebbian writeback, episodic recall, and post-turn consolidation. Local-first, model-agnostic, AGPL.
The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama/vLLM. BSL 1.1, auto-converting to Apache-2.0 on a two-year clock. Your AI keeps running when theirs doesn't.