llm-agents

Photo-agents

Python

77

Autonomous self-evolving agents. Vision-grounded layered memory and self-written skills for LLM agents that operate your computer.

mirage

TypeScript

85

The World's First Unified Virtual Filesystem For AI Agents

forsy-trace-skill

Python

67

Open skill for capturing AI agent work as structured traces.

llm-space

TypeScript

90

A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for managed agents.

deja-vu

Go

77

Your agents already solved this. deja finds it — memory operations for fifteen coding agents: retroactive search and MCP recall (84.9% R@1 on LongMemEval-S, no LLM), trust scopes, curated notes with tags and lifecycle states, measured impact. One zero-dep binary, fully local.

awesome-llm-apps

Python

95

100+ AI Agent & RAG apps you can actually run — clone, customize, ship.

browser-use

Python

95

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

sample-specship

Shell

73

Spec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation, and anti-slop quality gates. Packaged as a Kiro Power.

evonic

Python

77

Open Agentic AI Platform - The home your agents deserve

omnigent

Python

85

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.

Flowise

TypeScript

90

Build AI Agents, Visually

local-llm

Shell

77

Everything I know about running LLMs locally

harness

Swift

77

AI-driven user testing for iOS Simulator, macOS apps, and web apps. Write a goal in plain language; an LLM agent drives the UI and reports friction. macOS 14+, Swift 6.

llama.cpp

C++

90

LLM inference in C/C++

Investbrain

PHP

77

Smart LLM-enabled investment tracker that consolidates and monitors market performance across your different brokerages

chorus

TypeScript

72

Multi-LLM peer review for code decisions. Bring your own CLI; Chorus convenes 2-4 other LLMs to review the work before you ship.

shard

Python

77

Pipeline-parallel LLM inference across GPUs on separate machines.

voidllm

Go

72

Privacy-first LLM proxy and AI gateway — load balancing, multi-provider routing, API key management, usage tracking, rate limiting. Self-hosted. Zero knowledge of your prompts.

tokenspeed

Python

85

TokenSpeed is a speed-of-light LLM inference engine.

MLX-LoRA-Studio

Swift

77

A native Mac App for LLM fine-tuning on Apple Silicon — fully on-device, fully open source.

inference-school

Swift

82

A hands-on Swift and Metal course for building LLM inference from first principles on Apple silicon, with 48 guided lessons, runnable exercises, a native macOS Studio, and a complete companion book.

feeds.fun

Python

72

News reader with tags, scoring, and LLM

langchain

Python

95

The agent engineering platform.

waggle

Rust

80

Attributed, resolvable artifact references for agent handoffs — a ~30-byte token instead of pasted context. MCP-native; the reference layer for the agent-harness world.

ECC

JavaScript

95

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

ponytail

JavaScript

95

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

openwiki

TypeScript

95

OpenWiki is a CLI that writes and maintains agent documentation for your codebase.

zep

Python

90

Zep | Examples, Integrations, & More

hermes-agent

Python

85

The agent that grows with you

AutoGPT

Python

95

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

firecrawl

TypeScript

95

The API to search, scrape, and interact with the web at scale. 🔥

loop.js

TypeScript

68

A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.

LocalAI

Go

95

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

dify

TypeScript

95

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

unsloth

Python

90

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

filetree-skill

Python

67

A Claude Code plugin that maintains `FILETREE.md`.

directional-prompting

72

Outcome-first plus directional language. A two-layer skill for writing prompts, agent directives, and skill descriptions. Works in Claude Code and Codex CLI.

open-webui

Python

95

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

market-pilot

JavaScript

68

Evidence-grounded market research prototype with traceable AI workflows.

appless

TypeScript

82

What if your phone had no apps

lora-speedrun

Python

73

Speedrunning LoRA fine-tuning: frozen task, frozen hardware, public wall-clock leaderboard. modded-nanogpt for fine-tuning.

gemma-chat

TypeScript

80

Local AI chat + coding agent for Apple Silicon, powered by Gemma 4 via MLX / Supports Ollama

SiliconScope

Swift

82

Sudoless Apple Silicon system monitor (native SwiftUI GUI) with ANE / Media Engine / memory-bandwidth tracking

mdflux

Svelte

77

Turn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models.

transformers

Python

90

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

ragflow

Go

90

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Flawless

Python

80

AI SRE AgenticOps for Kubernetes and cloud infrastructure.

klaatcode

TypeScript

77

Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the right AI model for each task, cutting costs 10x. Supports Claude, GPT, Gemini, DeepSeek & more.