Open-source alternatives to Patchdiff Ai

The foundation layer for agentic intelligence.

Automated Documentation: Generates a parallel docs.md file for every notebook you run. - Context-Aware: Uses information from previous cells to understand the flow of your code. - Significance Filtering: Smartly ignores trivial cells (imports, prints, magic commands) to focus on the logic. -…

English | 简体中文

deepagents-backends provides production-ready implementations of the LangChain Deep Agents' BackendProtocol for remote file storage, allowing your agents to maintain state across restarts and share files in distributed environments.

A toolkit for developing AI agents.

Claude Code's compaction engine, as a drop-in DeepAgents middleware.

Rust library for building and running BPF/eBPF modules

Sample project demonstrating how to use eBPF to encap/decap packets with an MPLS label.

Examples and hands-on labs for Linux tracing tools workshops

The GenAI Toolbox is a framework designed to integrate large language models with structured databases, enabling autonomous data analysis and information retrieval. It functions as an agentic orchestrator that translates natural language prompts into executable database queries, allowing users to interact with complex data sources through conversational interfaces. The system distinguishes itself by utilizing schema-driven metadata serialization, which maps database structures into formats that language models can interpret to perform autonomous reasoning. By maintaining stateful conversation

LLMs struggle when asked to generate or modify large JSON blobs. trustcall solves this by asking the LLM to generate JSON patch operations. This is a simpler task that can be done iteratively. This enables:

This repository is inspired by and modified from Coinbase's CDP Agentkit. We extend our gratitude to the Coinbase Developer Platform team for their original work. For the voice agent, we extend the work of langchain-ai/react-voice-agent.

BCC is an eBPF development toolkit and tracing framework used for monitoring and analyzing the Linux kernel. It functions as a performance analysis tool and debugging utility to capture system events, measure kernel latency, and provide network observability. The project distinguishes itself by providing a build system that integrates with LLVM to compile C-like code into BPF bytecode at runtime. It utilizes BPF Type Format data for relocations to maintain cross-kernel compatibility and extracts kernel headers to ensure the generated programs match the specific kernel version. The toolkit co

Presentations and docs

This is a framework for building and deploying customizable AI agent services using a standardized reference architecture. It provides the core infrastructure necessary to host multiple agents within a single service, supporting interactive chat interfaces and real-time response streaming. The project distinguishes itself with a human-in-the-loop mechanism that allows agent execution to be paused for manual approval or intervention. It also features path-based routing to direct requests to specific agents and a multi-stage content moderation system to filter outputs through safety guardrails.

50% cost savings on LLM APIs with zero code changes.

The beginner's guide to eBPF

Hash-chained public record of verified agent settlements. Append-only, tamper-evident, auditable by anyone.

An EBPF based IPv4/IPv6 firewall with integrations for OpenZiti Zero-Trust Framework edge-routers and tunnellers

Prototyping kernel development work outside mainline

Sample BPF offload apps.

An example of an eBPF program hooking into the kill tracepoint

Visualize live LangGraph execution and see how your agent thinks as it runs.

Autonomous Mermaid to Flow-Animated GIF Converter

A tool for simulating conversations between an AI assistant and a virtual user for testing and development purposes.