Explore the directory

A single-file web app that turns natural-language requests into ready-to-run Bash or Python scripts and terminal commands tailored to Linux Mint 22.3, talking directly from the browser to a local or cloud LLM API with the user's own key.

• Coding agents

A TypeScript retrieval framework for AI agents that structures multi-source knowledge as resources, chunks, entities, facts and access-controlled evidence in a knowledge graph, instead of treating a corpus as a flat vector index.

• Agent memory
• RAG

A clean-room, pure-Rust, Git-compatible code forge built for autonomous coding agents as well as humans, centered on one immutable repository decision stream instead of a mutable bare repository paired with a separate database.

• Git

A collection of fake Python API modules for the Blender Game Engine (and its UPBGE fork), giving commonly used IDEs code completion for an API that is otherwise registered dynamically at engine startup.

• Editors

A serverless hybrid vector database Python client that fuses Amazon DynamoDB metadata storage with Amazon S3 Vectors approximate-nearest-neighbor search, running entirely inside a user's own AWS account.

• Databases

A lightweight, open-source terminal-first AI-native development environment built on Tauri, Rust and React, combining a PTY terminal, an IDE workbench, AI agents, Git and remote-environment controls in one desktop app.

• Editors
• Terminals

Experimental Rust codecs for vector quantization, including PolarQuant, TurboQuant and QJL, producing derived compressed representations for semantic-search candidate generation and KV-cache compression experiments.

• Inference
• Databases

A research environment that wraps a frozen language model in a persistent identity, memory, trust and governance loop, testing whether an agent's capability can come from surrounding structure rather than model weights alone.

• Agent frameworks
• Agent memory

A memory-aware GGUF inference runtime in Rust that runs quantized language models across CPU, NVIDIA CUDA, Apple Metal and Android without expanding weights into oversized resident copies.

• Inference

A local-first pocket agent app for iOS and Android that runs coding and general-purpose AI agent sessions on the phone, with a choice of model backend and approval-gated tool execution.

• Coding agents

A production-grade Python toolkit for retrieval-augmented generation that ingests PDFs, DOCX and XLSX into Qdrant with LLM-based metadata extraction, hybrid search and SHA256 deduplication.

• RAG

An all-in-one local inference platform that computes each model's launch flags to fit a user's VRAM, hot-swaps between chat, image and voice models, and serves them behind one OpenAI- and Anthropic-compatible API.

• Inference

A Persian-language translation of the English book Prompt Engineering for Beginners by Mark J. Baars, introducing beginners to designing effective prompts for AI language models.

• Books

A local-first retrieval-augmented knowledge base for the Pi and OMP coding agents, combining semantic embeddings with BM25 keyword search and code-aware chunking over a codebase, docs, PDFs and notes.

• Agent memory
• RAG

A durable, Git-versioned operating-memory layer for coordinating Codex, Claude Code and other agents on top of the Multica live-collaboration platform, distributed as an installable skill pack.

• Agent skills
• Agent memory

A Model Context Protocol server that exposes Teamwork.com's projects, desk, spaces and chat as tools an AI agent can call, over HTTP or STDIO, with bearer-token or OAuth2 authentication and a read-only mode.

• MCP servers

A local LLM call debugger that captures every API call an app makes to a language model during development, with full request and response detail, token usage, cost and latency, viewed in a local web UI.

• AI evals
• Debugging

A now-concluded research project that profiled a self-built NVFP4 LLM inference engine against llama.cpp and vLLM, found the custom engine was not the leverage point, and folded its findings into upstream contributions.

• Inference

A self-hostable AI agent with a built-in learning loop that creates and improves its own skills from experience, searches its past conversations, and can run on a $5 VPS or be reached through Telegram, Discord, Slack or a terminal.

• Agent frameworks

A consent-first research and product workspace for private AI agents, where individuals own their information through client-side encryption, scoped capability tokens and zero-knowledge memory storage.

• Agent frameworks
• Auth

An open-source CLI and editor plugin that installs a full tool-agnostic agentic coding setup — agents, skills, rules, commands, hooks and MCP integrations — into any repository for Claude Code, Cursor or GitHub Copilot.

• Agent skills

An MCP server that blocks a coding agent's claim_done until changes are verified on disk, enforcing a plan-then-gate-then-verify workflow instead of letting the agent self-report success in chat.

• MCP servers

A 22-lesson, project-driven curriculum on generative AI and LangChain agents, covering prompt engineering, vector embeddings, chain orchestration and building retrieval-augmented chat agents through hands-on examples.

• Tutorials

A file-based shared memory for AI coding tools that keeps tasks, bugs, plans and constraints synchronized across different agents and editors, so planning in one tool and coding in another loses nothing.

• Agent memory