Projects sharing features with Pi Autoresearch

Claude Code is a command-line interface and multi-agent orchestration framework designed for autonomous software engineering. It enables AI agents to perform codebase modifications, debugging, and Git workflow management while coordinating multiple specialized agents to decompose and execute complex engineering tasks in parallel. The system distinguishes itself through a high degree of isolation and safety, utilizing Git worktrees to create independent working directories for concurrent agents and implementing a tiered permission system that combines user rules, project policies, and OS-level

Speedtest-cli is a command-line utility designed to measure internet upload and download throughput by connecting to remote servers. It functions as a diagnostic tool for evaluating connection quality and verifying network performance against service provider claims. The utility identifies testing endpoints by calculating the physical distance between the client and available servers, ensuring measurements are based on responsive nodes. It manages the testing lifecycle by coordinating with remote services to fetch server lists and register results, which can be exported into machine-readable

Memori is an AI agent memory middleware platform designed to provide persistent, context-aware recall for language models. It functions as a non-intrusive layer that intercepts outbound model requests to automatically capture interaction history and execution traces, ensuring that agents maintain continuity across sessions without requiring modifications to existing application logic. The platform distinguishes itself through a dual-model storage architecture that maintains information as both structured relational primitives for precise fact retrieval and rolling narrative summaries for situ

This project is an algorithmic performance benchmarking tool and execution cycle simulator. It functions as a complexity analysis framework that measures code execution speed using simulated clock cycles to evaluate algorithmic efficiency against established performance baselines. The tool provides deterministic measurements of computational work and time complexity by tracking virtual clock cycles rather than real time. It utilizes a threshold-driven test suite to validate whether specific code implementations meet required performance cycle targets. The framework covers execution speed pro

benchmark.js is a benchmarking and statistical analysis library designed to measure and compare the execution speeds of JavaScript functions. It serves as a performance measurement tool that calculates mean execution time, margin of error, and standard deviation for specific code implementations. The library provides capabilities for comparing benchmark results to determine relative speed and manages organized test suites that can be run, cloned, or reset in bulk. It includes sampling precision controls to adjust minimum sample sizes and maximum run times to ensure statistical reliability. T

Scientist is a Ruby code parity testing library and production experimentation framework. It allows for the safe deployment of candidate code paths alongside a control implementation to verify that new logic produces the same outputs and exceptions as the original. The library identifies behavioral divergences between legacy and refactored code by running both versions in a live environment. It functions as a refactoring regression detector, measuring performance parity and detecting mismatches using real-world data without affecting the end user. The system covers broad capabilities for mon

This project is an AI agent workflow orchestrator and automated software lifecycle manager designed to sequence specialized AI personas for end-to-end software development. It serves as a prompt engineering library and a full-stack development toolkit that guides the process from initial discovery and specification through to deployment and code review. The system features a context management framework that utilizes progressive loading and routing tables to fetch reference files on-demand, reducing token consumption within the model context window. It employs a definition-based routing syste

Open Deep Research is an artificial intelligence framework designed to automate complex, multi-step research workflows. It functions as an autonomous agent that performs iterative web searches, analyzes retrieved data, and synthesizes information into structured reports. By decomposing broad queries into smaller sub-tasks, the system builds a comprehensive knowledge base to address open-ended questions. The platform distinguishes itself through an agentic loop that dynamically refines research strategies based on previous findings. It manages long-form data by compressing and summarizing cont

Sglang is a high-performance inference engine and serving system designed for large language and multimodal models. It provides a programmable interface for orchestrating complex generation workflows, enabling developers to coordinate multi-turn dialogues, tool invocations, and reasoning chains through a domain-specific language. The platform is built to support production-scale deployments, offering an OpenAI-compatible API that allows for integration with existing application ecosystems. The system distinguishes itself through a disaggregated architecture that separates compute-intensive pr

Local Deep Research is an autonomous research system consisting of an LLM research agent, a local model orchestrator, and a multi-engine search aggregator. It is designed to execute deep research by decomposing complex questions into atomic facts and synthesizing cited reports from academic, technical, and private document sources. The system features an encrypted research workspace that ensures zero-knowledge privacy through isolated, per-user encrypted databases. It utilizes a local RAG knowledge base to index research sources into searchable vector stores, allowing for retrieval-augmented

Kilocode is an autonomous engineering platform designed to orchestrate AI agents for complex software development tasks. It functions as a comprehensive system for automating coding, testing, and repository management by integrating directly with your codebase and terminal. The platform provides a unified gateway for model orchestration, allowing for the management of agentic workflows, event-driven automation, and persistent session state across distributed development environments. The platform distinguishes itself through its federated task management and policy-based access control, which

This project is a web-based interface designed to automate multi-step research tasks by synthesizing web data through large language models. It functions as an research assistant that combines automated search queries, web scraping, and model-based synthesis to generate comprehensive reports. The platform distinguishes itself through an iterative agentic orchestration loop that manages complex investigations, coupled with a provider-agnostic abstraction layer that allows for seamless switching between different language models and search services. Users can monitor the research process in rea

This project is a comprehensive framework for building and managing autonomous agent systems. It provides a unified architecture for orchestrating multi-agent societies, where specialized agents collaborate through roleplay to decompose and solve complex tasks. The system integrates language models with external environments, enabling agents to perform real-world actions through a standardized tool-calling abstraction layer. The framework distinguishes itself through its focus on iterative reasoning and data reliability. It employs automated feedback loops to refine agent outputs and self-eva

This project provides a framework for managing multi-agent systems, designed to automate complex software development, infrastructure, and business workflows. It functions as a multi-agent workflow orchestrator that routes tasks to domain-specific workers while maintaining state persistence and infrastructure automation. By leveraging large language models, the system decomposes high-level objectives into actionable plans, ensuring that complex operations are executed with consistency and reliability. The framework distinguishes itself through its hierarchical agent registry and policy-driven

Bash-Oneliner is a curated collection of reusable shell snippets and command-line patterns designed for system administration and data processing in Unix-like environments. It serves as a productivity guide for executing efficient terminal operations, text stream manipulation, and routine maintenance tasks using native shell primitives. The project focuses on modular command composition, allowing users to build complex workflows by chaining standard utilities through pipe-based data streaming. It emphasizes the use of POSIX-compliant shell execution and regular expression-powered text process

AzurLaneAutoScript is a mobile game automation system designed to perform repetitive gameplay tasks unattended. It functions as a screenshot-driven bot that controls Android devices, emulators, and cloud phones via ADB and uiautomator2, using computer vision to make interaction decisions instead of fixed timers. The project distinguishes itself through an advanced computer vision suite that includes local optical character recognition and perspective-aware grid detection. These tools allow the bot to parse 3D game maps, compute vanishing points, and normalize grid-centered objects for precise

Skim is a cross-platform interactive fuzzy finder that runs as a terminal application, a Rust library, a Vim and Neovim plugin, and a shell integration tool. It provides real-time filtering and selection from lists of items, supporting keyboard and mouse navigation, live preview panes, and multi-select functionality across Linux, macOS, and Windows. The tool distinguishes itself through a composable query expression tree that supports fuzzy, exact, inverse, prefix, suffix, and logical AND/OR operators, combined with a Smith-Waterman scoring engine that penalizes typos and gaps for natural rel

SalesGPT is an AI-powered sales agent platform that autonomously handles customer conversations, schedules meetings, and manages sales pipelines using language models. It is built on the LangChain framework and orchestrates multi-stage sales dialogues across voice, email, and messaging channels, grounding responses in product knowledge to reduce hallucinations and answer inquiries accurately. The agent guides conversations through predefined stages such as Introduction, Qualification, and Close using a state machine that tracks progress, while a reactive tool loop selects and executes externa

Mimiclaw is a framework for integrating large language models with microcontroller hardware to create interactive AI agents. It provides an embedded AI agent runtime and a tool-calling engine that allows language model loops to execute on embedded devices. The system acts as a bridge between language model APIs and physical hardware peripherals, enabling the control of sensors and actuators through natural language. The project features a dedicated manager for over-the-air firmware updates, allowing system images to be installed via web browsers or wireless networks to remove local toolchain

Goose is an autonomous coding assistant and extensible AI agent framework designed to automate software development workflows. It functions as an orchestration engine that can install, execute, and test code, as well as manage local files and shell commands. The platform is model-agnostic, providing a flexible interface to connect with diverse cloud-based or self-hosted large language model providers. It distinguishes itself through a standardized context protocol for integrating external tools and extensions, and a recipe system that allows users to define and repeat complex, multi-step AI w

mistral.rs is an inference engine for large language models that runs locally and exposes models behind OpenAI and Anthropic-compatible APIs. It serves as a multi-model serving platform, capable of loading several models in a single server process with per-request routing and on-demand loading and unloading. The engine supports multimodal inference, processing text alongside images, video, audio, and speech inputs, and includes a quantized model deployment runtime that reduces memory use and speeds up inference on consumer hardware. The project distinguishes itself through an agentic tool exe

Autocannon is a Node.js HTTP load tester and benchmarking utility used to measure server throughput and latency. It functions as a high-performance request generator designed for stress testing web servers and APIs to analyze request-per-second capacity. The tool operates as a distributed HTTP load generator capable of aggregating results from multiple machines. It also functions as a HAR file replay tool, allowing users to reproduce specific network traffic patterns by replaying recorded HTTP archive files. The project covers broad capability areas including HTTP traffic simulation through

Atmosphere is a Java-based framework for building and coordinating AI agents. It provides a real-time transport layer for streaming data via WebSockets, SSE, gRPC, and WebTransport, alongside a multi-agent orchestration framework for managing agent fleets through sequential, parallel, and graph-based execution workflows. The project features a durable workflow engine that persists agent state as snapshots, allowing long-running tasks to survive system restarts and incorporate human-in-the-loop approvals. It also implements Model Context Protocol servers to expose tools, resources, and prompt

Miroflow is an agent orchestration framework designed to coordinate multiple large language models and autonomous agents to perform complex research and reasoning tasks. It functions as a hierarchical workflow manager that distributes workloads across specialized agents using intent recognition and structured planning to gather deep information and solve challenging queries. The system distinguishes itself through a multi-model integration gateway and a provider-agnostic interface, allowing it to unify various language model providers. It extends these models via a tool-augmented framework th

BenchmarkDotNet is a library and tool suite for measuring the execution time and memory allocation of .NET code. It utilizes statistical sampling and warm-up iterations to determine the stability and precise execution speed of specific methods. The project provides a JIT disassembly viewer to inspect processor disassembly and analyze how the compiler executes code paths. It includes a memory allocation profiler that tracks managed and native memory traffic to identify efficiency bottlenecks. Additionally, a runtime performance comparator allows the same benchmarks to be executed across differ

This project is an AI-powered development workflow orchestrator that integrates autonomous coding agents directly into code editors. It functions as a framework for managing multi-agent systems, enabling developers to automate complex tasks such as code refactoring, inline completion, and multi-stage software development workflows. By utilizing a standardized communication protocol, it bridges the gap between local development environments and large language models. The system distinguishes itself through its focus on agent-based task orchestration and granular configuration. Users can define

Autoresearch is an autonomous machine learning research agent and architecture search framework. It employs a closed-loop system to programmatically rewrite training and architecture source code to discover optimal language model configurations. The system iteratively modifies code and evaluates performance metrics to improve model quality based on a target objective. It optimizes model performance and training efficiency by tracking validation bits per byte, which allows for a fair comparison of architectural changes independently of vocabulary size. The framework manages the full training