Search results

Pi is a terminal-based minimal coding agent harness built to adapt to user workflows rather than requiring users to adjust their processes. It supports 15+ providers and hundreds of models, offers tree-structured shareable interaction history, context engineering features, and four operation modes: interactive, print/JSON, RPC, and SDK. Users can customize Pi with extensions, skills, prompt templates, and themes, and share customizations as packages via npm or git. It is installable via curl, PowerShell, npm, pnpm, or bun.

piia-engram

github.com

piia-engram is described as a local-first AI memory that can be seen, edited, and overridden. It is portable across Claude Code, Codex, Cursor, Windsurf, and other MCP coding tools. The project presents a user-owned identity layer stored in local files.

Poirot

github.com

Poirot is a native macOS companion app for Claude Code. Built with SwiftUI, it lets users browse sessions, explore diffs, and re-run commands. It also provides session analytics, usage limit gauges, conversation views, and search across sessions. The app requires no login and no analytics and works offline.

Ponytail 5 is a ruleset for AI coding agents intended to make them write the least code that works. It provides a review command and an audit command, and states tests accompany risky logic. The project reports benchmark comparisons against running without it.

Ponytail

github.com

Ponytail is a GitHub repository or organization with source code, releases, documentation, or project resources.

poorcoder

github.com

Lightweight Bash scripts that enhance your terminal coding workflow with web-based AI assistants like Claude or Grok.

Prediction Guard

predictionguard.com

Prediction Guard is a self-hosted AI control plane described as enforcing NIST and OWASP-aligned runtime controls inside an organization's security boundary. It offers Agent Forge for creating interactive and autonomous agents, and an OpenAI, Anthropic and MCP compatible API. The site lists a Docker Verified Publisher agentic program entry and a verified Agent Control Kit on Docker Hub.

Prodmodel

github.com

Build tool for data science pipelines.

Product Manager Skills

github.com

Product Manager Skills is an open-source resource hosted on GitHub, created for use with AI coding tools including Claude Code, Codex, Cursor, and Windsurf. It provides support for product management tasks such as diagnosing SaaS metrics, critiquing product requirement documents, planning product roadmaps, running discovery work, and coaching product managers through career transitions.

Promptly

trypromptly.com

Promptly is a no-code generative AI platform built for enterprise use. It allows users to build generative AI applications, AI agents and chatbots without coding experience, and supports features including model chaining, RAG pipeline creation, custom data integration, and multi-language translation. The platform offers pre-built templates for common use cases.

Teaching page by John M. Zelle, Ph.D., for an introductory computer science textbook written in Python and published by Franklin, Beedle & Associates. It links edition-specific public resources for four editions and offers graphics.py, a simple graphics library released under the GPL for introducing object-oriented concepts. Instructor resources including problem solutions and exam questions are available from the publisher.

Qwen Lm

github.com

Qwen is a GitHub organization presenting Alibaba Cloud's general-purpose AI models, with 60 repositories. Public projects include Qwen3.8, a large language model series, Qwen3-VL, a multimodal large language model series, and qwen-code, an open-source AI coding agent that lives in a terminal.

Qwen3-Coder

github.com

Qwen3-Coder is the code version of the Qwen3 large language model series from the Qwen team. It is offered in multiple sizes, including Qwen3-Coder-480B-A35B-Instruct, Qwen3-Coder-30B-A3B-Instruct and Qwen3-Coder-Next, and the repository supports platforms such as Qwen Code, CLINE and Claude Code.

Rapid-MLX

github.com

Rapid-MLX is an open-source, Apache 2.0 licensed large language model inference server and Mac application for Apple Silicon devices. It is compatible with OpenAI and Anthropic APIs, built on the MLX framework, and focused on reliable tool calling for coding agents.

Repomix

github.com

Repomix is a GitHub-hosted tool that compresses an entire software repository into a single AI-friendly file for use with large language models and other AI tools including Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama and Grok.

ReviewCerberus

github.com

ReviewCerberus is an AI-powered code review tool that analyzes git branch differences and generates review reports. It examines logic, security, performance and code quality, and supports AWS Bedrock and Anthropic API, according to the repository. A GitHub Action posts review comments on pull requests.

sczhou/codeformer

replicate.com

CodeFormer, developed by sczhou, is a robust open-source face restoration algorithm designed for restoring old photos and AI-generated faces. The associated web demo is intended for research purposes. It is available via the Replicate platform or for local deployment, runs on Nvidia L40S GPUs, and typically completes predictions in 3 seconds. The associated research was published at NeurIPS 2022.

SEAL LLM Leaderboard

labs.scale.com

The SEAL LLM Leaderboard is a resource from Scale Labs that provides expert-driven benchmarks and updated rankings for large language models. It evaluates capabilities including agentic coding, frontier reasoning, and safety alignment, with over 20 benchmarks and assessments of more than 100 models from leading AI labs and open-source contributors.

superpowers

github.com

Superpowers is an agentic skills framework and software development methodology for coding agents. It prompts the agent to clarify a specification, shows the design in chunks for sign-off, then builds an implementation plan emphasizing red/green TDD, YAGNI, and DRY. A subagent-driven-development process has agents work through engineering tasks and review their work. Skills trigger automatically.

SymbolicAI

github.com

A neuro-symbolic framework for building applications with LLMs at the core.

Tabnine

tabnine.com

Tabnine is the AI code assistant that accelerates and simplifies software development while keeping your code private, secure, and compliant.

Terminal-Bench

tbench.ai

Coding agents help developers plan, implement, review, test, and debug software. For independent capability comparisons, see SWE-bench and.

The Methods Corpus Papers With Code

huggingface.co

Your daily dose of AI research from AK.

Tura

github.com

Tura is an open-source agent runtime harness that turns a task into a runtime-managed command graph, avoiding repeated model round trips in a ReAct session. The documentation describes it as a terminal-native developer tool that turns intent into verified code changes, emphasizing reading the repository first, keeping an audit trail, and proving results.