Projects sharing features with Codebase Memory Mcp

Potpie is an LLM codebase analysis platform and multi-agent orchestration framework designed to act as an AI software engineer. It parses repositories into a structured code knowledge graph, enabling AI agents to perform multi-hop reasoning, dependency tracing, and grounded technical analysis across large codebases. The system distinguishes itself through a spec-driven development framework where agents generate detailed technical specifications and architecture plans before implementing multi-file code changes. It utilizes a durable execution engine to coordinate specialized AI personas for

Headroom is an AI gateway proxy and token optimizer designed to reduce the cost and latency of large language model interactions. It functions as an intermediary that intercepts traffic between clients and providers to apply context compression, request routing, and format translation. The system differentiates itself through a Model Context Protocol server implementation that delivers compression and retrieval tools to compatible AI hosts. It employs a content-aware compression pipeline and tiered importance scoring to trim redundant data from logs and tool outputs while preserving essential

Hound is a self-hosted source code search engine designed to index multiple repositories for high-performance regular expression queries. It serves as a multi-repository code indexer that provides a centralized interface for searching across large-scale, private, and versioned codebases. The system utilizes trigram-based indexing to enable fast pattern matching and regular expression lookups without scanning every file. To maintain current search results, it employs automatic synchronization through a combination of periodic polling of remote version control systems and monitoring of local di

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

This project is a static code analysis tool and local-first code indexer that builds a persistent dependency graph of functions, classes, and imports. It functions as an AI context optimizer and codebase dependency graph, designed to reduce token usage by providing AI assistants with only the most relevant code fragments and impact analysis for a given change. The system implements a Model Context Protocol server that exposes code intelligence and architectural graph queries to external AI coding tools. It distinguishes itself by computing the change blast radius and risk scores of modificati

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

Apache AGE is a graph database extension for PostgreSQL that adds openCypher graph query capabilities directly within the relational database environment. It functions as a loadable extension that translates Cypher graph traversal queries into SQL expressions, enabling users to run pattern matching and path analysis alongside standard SQL operations within a single database instance. The extension stores labeled, directed property graphs as isolated schemas with internal relational tables for vertices, edges, and labels, preventing cross-graph interference. It supports hybrid query execution

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

Tempest is an orchestration platform designed for the execution and management of autonomous coding agents. It provides a framework for running multiple agents in parallel, coordinating their workflows, and maintaining persistent session states through a centralized management interface. The platform distinguishes itself through its focus on secure, isolated execution and intelligent context management. Each agent operates within a dedicated sandbox, utilizing ephemeral file systems and database copies to perform tasks without impacting production environments. To optimize performance and red

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

Kreuzberg is a document extraction engine that converts PDFs, Office files, images, and over 90 other formats into clean, structured text and metadata. It is built around a compiled Rust core that can be used as a native library, a command-line tool, a REST API server, or a WebAssembly module for browser-based processing. The system is designed to run entirely on self-hosted infrastructure, with no data leaving the user's environment. What distinguishes Kreuzberg is its breadth of integration surfaces and its pipeline architecture. It exposes extraction capabilities through native bindings fo

Treg is a gateway that lets AI agents search a catalog of third-party API endpoints and call any of them with a single token. Each request is routed to a working provider, and the service attaches the stored provider key on the server, so agents and scripts never handle raw secrets. It is also exposed as a Model Context Protocol server with OAuth sign-in, so coding assistants such as Claude and Cursor can reach catalog tools and team tools through one interface. What sets it apart is the combination of routing, billing and shared credentials. Calls are billed per use against a prepaid team ba

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

Oh My Hermes (Hermes Orchestrator) is a workflow layer that sits on top of the Hermes agent runtime. It routes requests to staged skills, external coding executors, and verification gates, through chat or a terminal interface. Completion is evidence-gated: every status carries a stage and confidence, and work is marked verified only after tests, reviews, or CI checks have actually passed. It is also distributed as a catalog of installable workflow skills and plugin hooks, for Hermes and other coding-agent hosts. Its main focus is multi-agent coding delegation. Scoped tasks are handed to codin

This project is a build orchestration engine and development toolkit designed for managing large-scale monorepos. It provides a unified workspace environment that maps project relationships and dependencies, enabling the system to perform intelligent impact analysis and execute only the tasks affected by specific code changes. The system distinguishes itself through a persistent daemon that monitors file changes for near-instant feedback and a content-addressable caching mechanism that stores task outputs to prevent redundant computation across local and remote environments. It further suppor

Obsidian Mind is an Obsidian vault template that gives AI coding agents persistent, linked memory. Knowledge is stored as git-tracked markdown notes with frontmatter and wikilinks, so lessons, decisions and context carry over between sessions, repositories and machines. One shared instruction file, set of hook scripts and set of commands serve Claude Code, Codex CLI and Gemini CLI against the same notes. What sets it apart is how it manages agent context. A startup briefing loads goals, active projects, recent changes and open tasks under an enforced byte budget, shrinking low-value sections

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

CodeQL is a semantic code analysis engine and vulnerability scanning tool that treats source code as data. It utilizes a static analysis query language to define complex patterns and security vulnerabilities within a code graph database. The system represents source code as a relational database, enabling the execution of structural queries and data flow analysis. This approach allows for the detection of security flaws and coding errors across large-scale repositories. The tool provides capabilities for automated code auditing, static analysis security testing, and custom vulnerability dete

Switch is a self-hosted platform where people and AI agents share chat rooms. Agents built on different coding-agent harnesses, models or providers can join a room as teammates, and the system runs and coordinates their sessions on a laptop, over SSH, or on remote machines. Rooms can be bridged to channels on Slack, Microsoft Teams, Discord, Telegram and Mattermost, so teammates address agents in the tools they already use. Agent sessions are launched through native SDK or protocol adapters, with providers such as Claude Code, Codex, Cursor and OpenCode driven through one shared session inter

t3code is a platform for operating AI coding agents through a web interface to develop and maintain software projects. It functions as an orchestrator that manages AI agent lifecycles and communication, providing a system for provisioning isolated remote development environments and managing secure connections to cloud-hosted resources. The project utilizes an event-sourced backend architecture that processes typed commands into persisted domain events to maintain system state. It employs a communication system based on JSON-RPC over WebSockets to synchronize real-time state and events betwee

Free Code is a terminal-native AI coding agent that edits files, runs shell commands, and answers questions through natural language conversations directly in the command line. It operates as an interactive loop in the shell, providing direct filesystem manipulation without intermediate abstraction layers or sandboxing. The project distinguishes itself through a compile-time feature flag system that activates or deactivates 54 experimental capabilities, including voice input, multi-agent planning, and memory extraction. It also routes all AI requests to one of five supported API backends by s

PI-Desktop is a desktop application that runs an AI coding agent on your own machine against a local repository. Projects, sessions, settings, and logs are stored locally, credentials are kept in the system keychain, model requests go straight to your chosen provider, and no telemetry is collected. It is a persistent workspace, independent of any particular editor or terminal, that remembers its state between launches. It is available for macOS, Windows, and Linux. The agent can work in agent, plan, or goal modes: delegate a coding task and review progress, study a project and approve an impl

deepseek-harness is a TypeScript framework for building AI coding agents out of interchangeable plugins attached to a shared core runtime. Loops, tools, and services can be added, swapped, or removed through configuration rather than by rewriting code. The same agent platform is reachable through several front ends: a browser interface, a headless mode, an SDK, and automation entry points. Agents can drive external tools through Model Context Protocol servers and language servers, and can edit files and run shell commands in sandboxed workflows with approval prompts for sensitive actions. Fil

The sandbox-sdk is a development kit designed for building secure, isolated execution environments on a global edge network. It provides a framework for creating ephemeral, containerized workspaces that allow developers to run untrusted code, manage build tasks, and host automated scripts without compromising host system security. By leveraging a serverless runtime, the platform enables the deployment of these environments directly at the network edge to ensure low-latency performance. The platform distinguishes itself by integrating language models with sandboxed execution, facilitating the

TencentDB-Agent-Memory is a shared memory platform for large language model agents. It stores conversation facts, documents, code knowledge, and learned skills in one place, so later sessions can recall people, preferences, decisions, and context without users repeating themselves. Conversations are distilled asynchronously into layers: facts, scenario knowledge blocks, and long-term persona profiles. What sets it apart is that memory covers more than chat history. It indexes source code into a graph of files, functions, and call relationships so coding agents can look up callers and callees

Claudecodeui is an open-source web interface that orchestrates multiple AI coding agents from different providers—including Claude Code, Cursor CLI, Codex, and Gemini CLI—side by side in isolated cloud environments. It functions as a multi-provider orchestration platform, allowing users to run agents from different tools within the same workspace without being locked into a single vendor. The platform runs each agent session inside a hypervisor-level Docker sandbox that isolates filesystem, network, and process access, with sessions persisting in the cloud to survive network disconnection or

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