Language models95 projects
Large language models, runtimes, and the tools around them.
A modular, stack-agnostic toolkit of security review skills for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.
A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first.
Wireshark for MCP. A transparent proxy that shows every real tool call between your AI client and your MCP servers, live in your terminal.
Multi-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.
The Fable Workflow: how Claude Fable 5 worked, distilled into skills any model can run, with the eval that keeps it honest. Think / act / prove.
Zero-dependency browser video editor that AI agents can drive — JSON timeline, MCP + REST, live-reloading UI
✨ The agentic motion layer — an open-source, chat-native motion engine. Describe the feeling; your AI ships the animation.
A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, governance) for LLMs, SLMs, AI agents, and world models — with schemas, 159 skill cards, benchmarks, and CI.
The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of what agents read, evidence-driven risk, MCP memory for coding agents, signed provenance attestations. One command, offline by default.
Open-source, channel-native agent gateway for Slack. Route team threads to Claude Code, Codex, OpenCode, Docker, HTTP agents, and custom CLIs with policy, approvals, memory, audit logs, and artifacts.
Strip AI-writing tells from papers and grant proposals (NSF/NIH), while keeping scholarly voice and tying claims to evidence. A skill for Claude Code, Codex, and MorphMind.
Attention is your scarcest resource. Chief is the local-first layer that guards it — turning every agent, alert, and feed into one honest call: interrupt, or not.
The open-source AI workbench for scientific research
A reference operating model for organizations where any role can be filled by a human or an agent, every process is built for agents first, and every flow can be paused, adjusted by a human, and resumed.
An AI-agent skill that generates browser-editable presentations from multiple visual themes, exportable to HTML, PDF, and PPTX.
Product-design, conversion & behavioral-science principles for SaaS
GPU worker client for the Talos network. Pairs with your Talos account, serves open-model inference jobs over a WebSocket, and reports uptime for payouts.
Ground your AI coding agent in the books, standards, and docs you actually trust. A local MCP RAG server that makes your preferences the default.
A local-first, open-source coding agent for your desktop. Bring your own LLM key; your code stays on your machine and only ever leaves to the model provider. The AI Agent builds its own Harnes.
The first AI agent harness native to the browser. A browser extension that runs a full agent loop where you already work: it drives your tabs, spins up sandboxed compute (JS notebooks, WASM Linux VMs, client-side apps), and shares what it builds peer-to-peer. BYOK, no backend, no telemetry.
Open-source @agent mentions for Slack and GitHub. OpenTag routes tagged requests to Codex, Claude Code, then returns results in thread.
Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden imports, and gotchas to each file. The only context format validated in a controlled benchmark. Tool-agnostic; nothing injected into your source.
Open-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous self-correction layer add almost no token cost; 1M context, Skills/MCP/Hooks, Claude Code config compatible.
Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface
A curated, non-BS library of the best resources for building and evaluating AI agents — papers, blogs, talks, tools, benchmarks. Maintained by BenchFlow.
Persistent memory plugin for OpenCode. Obsidian-style knowledge base that survives across sessions
🤖 Building AI Agent Systems from Scratch — A comprehensive, practical tutorial from fundamentals to production-grade multi-agent applications
Open-source sandboxes for AI agents — run untrusted, AI-generated code safely on your own machine.
High-performance Knowledge Graph engine for AI, LLMs, and GraphRAG — built for the next generation of intelligent applications.
Forge a working, testable, publishable MCP server in 30s. TypeScript or Python, with example tools, the Inspector and tests included.
A Boris-style agentic orchestrator TUI that supervises headless Claude Code agents through a gated software-delivery pipeline — pointed at any repository.
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Floating macOS HUD for live Claude & Codex usage quotas — menu-bar toggle, threshold/recovery reminders, custom hotkey, dark/light. Reads Chrome cookies locally.
A tiny macOS menu bar status indicator for Claude Code: animated icons, elapsed timer, and open/close lifecycle.
Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code durable memory — entirely offline.
Reverse engineered Windows Copilot into an OpenAI-compatible API. Access GPT-4 and GPT-5 models through a simple REST interface without API keys or billing.
The definitive OpenAI, Claude, MCP, Harness, Evals, and Production Agent Systems learning roadmap.
Sudoless Apple Silicon system monitor (native SwiftUI GUI) with ANE / Media Engine / memory-bandwidth tracking
I-Ching oracle as a static site — three-coin method, Wilhelm translation, optional AI interpretation via local LLM servers (Ollama / MLX / LM Studio). Vanilla JS, zero dependencies, PWA, offline-capable, with native macOS app.
Intensity slider from tipsy (0.1) to blackout (1.0). 5 moods, 8 creative techniques. Lowers inhibition, not intelligence. Unfiltered genius for Claude Code.
A native Mac App for LLM fine-tuning on Apple Silicon — fully on-device, fully open source.
Self-hosted AI novel generator: single Go binary + web UI. OpenAI-compatible API → outline → chapter-by-chapter writing with review, foreshadowing, fact-check, and full-book polish. Chinese & English.
Ask several AI models one question — they answer in parallel, critique each other blind, and you decide. Native macOS, bring-your-own-keys.
DiffusionGemma-1B: Unified Architecture — 1:1 accurate reproduction of google/diffusiongemma-26B-A4B-it diffusion-specific components, adapted to a unified 1B-parameter architecture
A Claude Code plugin that makes Opus behave like Fable — completion, evidence, and verification enforced as procedure. Ships only what a Fable-vs-Opus comparison proved transferable.
AI workflow automation plugin for intelligent code generation with Claude/Codex
🪸 Powerlevel10k-inspired statusline for Claude Code — paste one prompt and your AI interviews you, then installs it
Transparent proxy for Claude Code that auto-routes image-bearing requests to a multimodal model — so a non-multimodal primary model never crashes your long-running sessions.
Community model zoo for Apple Core AI (iOS/macOS 27): 49 models — LLM, VLM, OCR, ASR, TTS, image/video/music gen, forecasting — converted, verified on real devices, downloadable from Hugging Face, and runnable in one line of Swift via CoreAIKit. Plus conversion recipes, on-device benchmarks, custom Metal kernels, and a knowledge base.
Open Dungeon — the first easy-to-use, fully local AI roleplay app. Story and inline scene images generated 100% on your machine (Gemma 4 QAT via Ollama(and others) + FLUX). No accounts, no API keys, no cloud.
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.
Your personal AI worker. Watches your screen, learns your workflows, automates the repetitive parts. Built on Screenpipe. All local, no cloud, no setup. It gets better every day without you doing anything differently.
Stop re-explaining your data to your AI every session. The individual-analyst context layer, delivered over MCP (Claude Code / Cursor / Codex).
Open-source gallery of AI-generated UI experiments built with Claude (Fable 5), landing pages, hero sections, GLSL shaders, design systems, animations & 3D in React, Tailwind & Three.js.
Inference-native Tokenmaxxing Agent Harness for Loop Engineering
A drop-in proxy that compresses bloated code context in real-time, cutting LLM API costs by 50–80% without losing what the model actually needs to know.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
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.
From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous batching, speculative decoding, a Rust gateway, a JAX oracle, and interpretability tooling.
Reusable Skills for LLMQuant Agent, Claude Code, Claude.ai, Cursor, Hermes Agent, OpenClaw and Codex, grounded in LLMQuant Data
End-to-end AI short-video production pipeline. FastAPI orchestration + Spring Boot gateway with multi-model failover, circuit breaker, metering, and full-stack observability. AI quality gating: prompt anchoring, CLIP consistency, AV sync auto-rescue.
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.
Open-source observability tool that uses AI agents to self-heal your software
Drop-in prompt-caching fixes for the LLM agent harness you use. Point your AI coding agent at this repo and it ships the patches.
Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs
Run Claude Design locally as an Agent Skill — Cursor, Claude Code & more. Produce polished UI mockups, prototypes, decks & wireframes as self-contained HTML, without claude.ai/design. Best with Opus 4.8.
GBase — Recursive Self-Improvement Agent Framework. Memory, evolution, quality gates, identity system, and 40+ auto-registered tools.
Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly.
KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.
Keep one source of truth for your AI coding-agent rules. Convert and sync between AGENTS.md, CLAUDE.md, .cursorrules, Copilot, Windsurf, Cline, Aider & Gemini — or scaffold a fresh AGENTS.md. Zero dependencies.
Give a query, get a dataroom. Pi + self-hosted Qwen3.6 research harness on a single L4.
An end-to-end framework for multi-speaker transcription that jointly models who spoke, when, and what.
A local control plane for AI agents — see what they do, approve what matters, keep secrets out. Rust + Tauri + Chrome MV3.
A hand-curated, topic-organized library of the best ML education — 923 docs (391 arXiv papers, 474 Stanford/MIT/Karpathy/fast.ai lectures, 58 explainer articles), normalized to Markdown with full provenance. Open it in Obsidian or point your agent at it. A clean ML corpus for learning, RAG & fine-tuning.
Seamlessly extend any image in any direction with AI. Open-source web app powered by Gemini via OpenRouter, with Poisson-blended seams and best-of-3 variant picker.
kalshi trading bot kalshi trading bot kalshi trading bot kalshi trading bot kalshi trading bot kalshi trading bot kalshi trading bot kalshi trading bot kalshi trading bot kalshi trading bot kalshi trading bot kalshi trading bot kalshi trading bot kalshi trading bot kalshi trading bot kalshi trading bot kalshi trading bot
The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.
Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 15 agents, 33 skills working with /goal, agent-team, & workflow on autopilot loops with 0 need for human gate. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack
gemini antigravity 2.0 cli google terminal ai agent tool agy migration guide mcp server plugin slash commands gemini 3.5 flash coding agent tool free
ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans out parallel divergent thoughts under different cognitive frames, scores, prunes traps, deepens the survivors. The no-brainer skill for creative and interdisciplinary work.