Projects sharing features with Cocoindex Code

OpenViking is a multi-tenant context server and knowledge base administration system designed to provide AI agents with persistent long-term memory. It enables the indexing of diverse documents and codebases to support retrieval-augmented generation, allowing agents to recall past interactions, user preferences, and learned experiences across sessions. The project is distinguished by its use of a URI-based virtual filesystem to organize memories, resources, and skills. It implements a tiered context loading system that balances retrieval precision with token budgets by structuring data into a

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

Semantica is a Python framework for building context graphs and knowledge graphs that AI agents can query, reason over, and audit. It ingests documents and data from many sources, extracts entities and relations, merges duplicates, resolves conflicting facts, and stores the result as connected nodes and edges. Each AI decision can be recorded as a graph node with its reasoning, causal links, and policy checks, and every fact carries W3C PROV-O lineage linked by hashes so its origin can be verified and exported as an audit trail. Reasoning is rule-based and explainable: forward chaining, Rete

This project is a Model Context Protocol server that connects large language models to web scraping and crawling tools. It functions as a bridge, allowing LLM clients to utilize a web crawling engine and scraping utilities to extract and process web data. The server integrates a markdown web converter that transforms dynamic web pages and PDF documents into clean markdown to optimize consumption by AI models. It also provides a browser automation interface for controlling headless sessions and bypassing access restrictions. The system covers broad capabilities including large-scale website d

This is a software development kit for integrating the Model Context Protocol into Java applications. It serves as a framework for building AI servers and communication layers that exchange prompts, resources, and tool definitions between AI clients and servers. The SDK provides a transport-agnostic communication layer, allowing bidirectional data exchange over standard I/O, HTTP, or Server-Sent Events. It includes a generative AI resource manager for exposing structured data and prompt templates, and a standardized interface for implementing protocol clients and servers. The project covers

Spartan is a development framework and design system toolset that combines a headless UI component library with a full-stack application scaffolder. It provides accessible, unstyled primitives that separate behavioral logic from visual styling, while automating the creation of development environments with end-to-end type safety across API and database layers. The project distinguishes itself by utilizing a component distribution model that copies styled source files directly into the local codebase to prevent dependency-based style locking. It also functions as an AI context server, using a

MoviePilot is a self-hosted media orchestrator and NAS media library automator. It coordinates workflows between downloaders, metadata scrapers, and file systems to automate the discovery, downloading, renaming, and organization of movie and television content. The system functions as an LLM media management agent, allowing users to control subscriptions, searches, and file organization through conversational text commands. It also acts as a Model Context Protocol server, exposing internal media management tools via a standardized interface for external AI clients and agents. The project inc

Xerj is a search engine for AI agents, shipped as a single static Rust binary with no JVM or Lucene dependency. It indexes code, documents, logs, PDFs and other files for keyword (BM25), vector and hybrid retrieval. It also acts as a persistent memory store with a knowledge graph, a Model Context Protocol server for coding agents, and an Elasticsearch-compatible server. A separate fact-answering mode responds to questions only from stored, source-quoted facts. The agent-facing side includes a stdio MCP server exposing search, memory, linking and code-lookup tools, plus a single init command t

This project is a self-hosted AI monitoring stack that functions as an LLM observability platform, AI evaluation framework, and OpenTelemetry trace analyzer. It is designed to capture and analyze LLM traces, sessions, and telemetry to monitor AI agent performance. The platform distinguishes itself as a Model Context Protocol server, exposing workspace functions as tools for AI coding agents. It enables the conversion of failing production traces into test datasets for regression testing and utilizes semantic-based session clustering to discover emerging user behavior patterns. The system cov

This project provides a collection of infrastructure components for multichain wallet integration, including a cryptographic library for cross-chain transaction signing and a curated repository for cryptocurrency asset metadata. It serves as a central hub for managing token logos, contract addresses, and technical specifications for digital assets across multiple blockchains. The system includes a Model Context Protocol server that exposes real-time blockchain data and technical documentation to large language models. It further extends this AI integration by providing a standardized tool-cal

CodeGraphContext is a code graph indexer and visualization tool that analyzes source code to build graphs of functions, classes, and inheritance relationships. It functions as a Model Context Protocol server, providing a structured codebase index to AI assistants for context retrieval and natural language querying. The project features an interactive web interface that uses force-directed layouts to visualize code dependencies and symbols. To accelerate the setup of large projects, it supports the import of pre-calculated knowledge bundles for popular repositories. The system provides capabi

Gauzy is an open business management platform and multi-tenant enterprise resource planning system. It provides a modular business framework designed to manage core organizational operations through a unified web interface or as a headless business API. The platform is distinguished by its integration with the Model Context Protocol, allowing it to act as a server that exposes business data and system functions as tools for AI assistants. It utilizes a dynamic plugin architecture and a dedicated marketplace to extend core business entities and services. The system covers a broad range of ope

Ever Gauzy is an integrated business management suite providing an ERP and CRM framework for professional services automation. It functions as a multi-tenant SaaS platform that combines time tracking, billing, and human resource management into a unified system. The project is distinguished by its headless architecture, utilizing a REST and GraphQL API gateway to expose business operations. It features a Model Context Protocol server that allows AI assistants to interact with system data and execute functional tools for automated business workflows. The platform covers a broad operational su

This project is a Model Context Protocol server that enables artificial intelligence assistants to interact directly with Microsoft Excel files. It functions as a bridge, allowing external systems to read, write, and modify spreadsheet data through a standardized interface. By supporting both direct file manipulation and headless application automation, the server provides a comprehensive utility for programmatic workbook management. The server distinguishes itself by combining data processing capabilities with a visual rendering pipeline. It can generate image snapshots of specific spreadshe

OpenSandbox is a secure sandbox runtime and containerized code execution engine designed to run AI-generated code and scripts in isolated environments. It serves as a workload orchestrator that prevents host system contamination by utilizing kernel-level isolation to execute arbitrary commands and scripts. The project distinguishes itself by providing a model context server that bridges large language models to the sandbox for performing file operations and system commands. It also includes a remote GUI sandbox that supports browser automation and desktop interfaces via remote access protocol

btrace is a JVM dynamic tracing tool and performance profiler used for injecting safe instrumentation scripts into a running Java Virtual Machine without requiring a process restart. It functions as a Java agent framework and a Model Context Protocol server, exposing JVM diagnostic operations and tracing tools to large language models and AI assistants. The project distinguishes itself by enabling real-time code injection and bytecode-level instrumentation via a secure binary protocol. It ensures production stability through a static safety analysis engine that blocks unstable code patterns,

This project is an autonomous workflow engine and orchestration platform designed to coordinate specialized AI agents. It functions as a development framework that manages the end-to-end lifecycle of complex, multi-step tasks, including persona definition, persistent memory management, and the execution of automated coding workflows. By acting as a Model Context Protocol server, it enables standardized communication between development tools and external AI models. The platform distinguishes itself through an event-driven architecture that routes typed messages between agent personas, allowin

gbrain is an agent framework and retrieval-augmented generation system that combines a durable task queue, a git-synced vector store, and a knowledge graph engine. It provides a foundation for building AI agents that interact with structured knowledge bases using the Model Context Protocol. The system synchronizes markdown files from a git repository into a database for high-performance semantic retrieval and creates typed edges between data pages by extracting entity references and wikilinks. It uses a database-backed queue to execute persistent background jobs and tool loops, ensuring relia

AgentMemory is a persistent knowledge store and memory server designed to provide AI coding agents with long-term memory. It functions as a knowledge graph engine and vector database store that saves and recalls project context, architectural decisions, and patterns across different sessions. The system distinguishes itself by using a tiered-memory consolidation pipeline that compresses raw observations into episodic, semantic, and procedural layers to optimize token usage. It employs a hybrid retrieval strategy combining keyword matching, vector embeddings, and graph traversal to surface rel

M-Flow is a graph-based long-term memory engine for LLM agents and chatbots. It stores knowledge as a four-level hierarchy of whole episodes, topical facets, atomic facts, and entities, and retrieves it by scoring the strongest chain of typed, weighted graph links between each memory and the query, rather than relying on vector similarity alone. Agents can keep episodes, facts, entities, and learned habits across conversations. Retrieval goes through a single entry point that selects among episodic, procedural, triplet, lexical, and graph-query modes, trading accuracy against simplicity or cu

zvec-grep is a command-line search tool that indexes a folder of code, documents, and structured data once and returns ranked, source-linked passages from the terminal. It runs on macOS, Linux, and Windows and is built for coding agents to pick up on their own, though people can also preview ranked passages directly. Each hit maps back to exact source line coordinates, with short or full previews and highlighted matches. Search combines meaning-based and keyword matching: keyword ranking and vector similarity are fused into a single list, and each query can run in hybrid, full-text, or vector

Codegraph is a local codebase indexer and static analysis graph database that serves as a context provider for AI agents. It parses multiple programming languages into a searchable knowledge graph of symbols and dependencies, exposing these relationships to AI tools through the Model Context Protocol. The project distinguishes itself by aggregating relevant code snippets and symbol flows to reduce token usage for large language models. It automates the configuration of server settings and steering instructions across various AI agent platforms and command line editors to enable automatic code

This project is a Model Context Protocol server and AI agent database connector. It provides a standardized communication layer that allows language models to interact with relational data stores, read database schemas, and manage PostgreSQL database resources. The implementation acts as a serverless host for the Model Context Protocol, deploying on distributed edge functions to connect AI assistants to a project. This enables AI agents to perform database administration, execute SQL queries, and handle schema migrations through an AI-compatible interface. The system covers broader capabilit

k8sgpt is a suite of Kubernetes-focused tools designed for AI-powered debugging, cluster diagnostics, and self-healing. It functions as an automated analyzer and debugger that uses large language models to explain cluster errors, suggest remediation steps, and identify resource failures. The project distinguishes itself through an extensible analysis framework that supports custom diagnostic plugins and a Model Context Protocol server, which exposes cluster diagnostics as tools for AI assistants. It includes a self-healing agent capable of automatically generating and applying fixes for detec

Qodo Cover is an engineering governance platform and AI-powered assistant designed for automated code review and unit test generation. It utilizes an abstract syntax tree codebase knowledge graph to map dependencies and architectural relationships, allowing it to analyze pull requests and enforce organizational coding standards. The system distinguishes itself through a multi-agent analysis pipeline that performs architectural reasoning and identifies bugs beyond the immediate diff. It features a model context protocol server to expose codebase intelligence to external tools and can automatic

kubefwd is a Kubernetes network tunneling and service forwarding utility that maps remote cluster services to local loopback addresses. It synchronizes the local hosts file to resolve Kubernetes service names to local IP addresses, enabling local development environments to use production hostnames. The project implements a Model Context Protocol server, allowing external AI assistants to discover, browse, and control network forwarding through a standardized interface. It also provides a terminal user interface for managing service forwards, monitoring real-time network traffic, and streamin

Horizon is an AI-powered news aggregation system designed to build custom pipelines that fetch, filter, and enrich information from diverse web sources. It utilizes large language models to automate information filtering, scoring content to remove noise and highlight high-value stories. The system integrates the Model Context Protocol to expose pipeline stages as tools for external AI assistants. It employs a unified adapter to standardize diverse AI model providers for consistent content scoring and summarization tasks. The pipeline aggregates data from RSS feeds, social platforms, financia