Search awesome repositories

Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs.

:checkered_flag: Django Start Project template with batteries

Build fast, user-friendly applications with Django and React or Vue

40K, small memory footprint, single binary that run list of commands in parallel and waits for their termination

The simplest way to scale Python.

Coding super-intelligence to find the most optimized Python code. Use it to optimize existing codebases or new Pull requests as a GitHub Action or a VS Code Extension.

No description.

:bowtie:Yet Another BGP Python Implementation

Open Python agent harness for production AI apps: tools, MCP, memory, workspace, telemetry, subagents, background tasks, and OmniServe APIs.

Relevance Vector Machine implementation using the scikit-learn API.

Django starter kit that focuses on good defaults, developer experience, and deployment. Updated for Django 5.2.

A self-hosted API to fetch and mix entries from Atom and RSS feeds (returns Atom, RSS, or JSON)

🔎 A MCP server for Unsplash image search.

Our production ready (too much) opinionated django template

⚡ The fastest way to build Apps in ChatGPT

Unofficial wrapper for Substack's API

⚡ The fastest way to build Apps in ChatGPT

Schema, functions and a python library for storing and accessing STAC collections and items in PostgreSQL

2X faster ASGI web framework for python, offering high-level development, low-level performance.

K8s-mcp-server is a Model Context Protocol (MCP) server that enables AI assistants like Claude to securely execute Kubernetes commands. It provides a bridge between language models and essential Kubernetes CLI tools including kubectl, helm, istioctl, and argocd, allowing AI systems to assist with cluster management, troubleshooting, and deployments

Model Context Protocol (MCP) implementation for Opik enabling seamless IDE integration and unified access to prompts, projects, traces, and metrics.

Lightweight OpenHands CLI in a binary executable

BatchFlow helps you conveniently work with random or sequential batches of your data and define data processing and machine learning workflows even for datasets that do not fit into memory.

Detect N+1s in your Django app.

A Rust crate and Python library for packed, immutable, zero-copy spatial indexes.

binary ninja cli for coding agents

No description.

Geospatial extension for Polars DataFrames.

Local-first MCP tools and dashboard for investigating Codex token usage, credits, costs, caching, and thread patterns.

A lightweight service that enables AI assistants to execute AWS CLI commands (in safe containerized environment) through the Model Context Protocol (MCP). Bridges Claude, Cursor, and other MCP-aware AI tools with AWS CLI for enhanced cloud infrastructure management.