Tools tagged with "Context compression"

Headroom compresses the material an AI agent reads before it reaches the model. It's for developers whose LLM apps or coding assistants spend context space on repetitive tool results, logs, files, and retrieved documents. Compression runs on your machine, and no prompt or file content goes to an external service for compression. Requests still go to your chosen LLM provider.

Mem0 is a memory layer for developers building AI agents and assistants that need to recall earlier interactions. It retains user, session, and agent context across conversations, so an assistant can remember preferences or a support bot can refer to past tickets. The self-hosted code is open source under Apache 2.0; Mem0 also has a managed service.

Pi is a terminal-based coding assistant for developers who want to shape the agent around their own workflow. Its core stays small, while extensions can change its tools, commands and terminal interface. It's open source under the MIT license.

RisuAI is an open-source AI roleplay client for people who want to create characters, build fictional worlds and chat with several characters together. It runs on Windows, macOS, Linux, Android and in a browser. You can also host the web app yourself with Docker.

NextChat is a self-hosted AI chat interface for people who want one place to use their own LLM server and cloud models. The web and desktop project is open source under the MIT license. You can host it with Docker or on Vercel, and desktop clients run on macOS, Windows and Linux.

Skills (mattpocock) is an MIT-licensed collection of engineering workflows for developers using Claude Code, Codex and other AI coding agents. Its small, separate skills work with any model and can be combined or adapted to your project, so you can choose specific practices without adopting an entire development process.

AG2 is an open-source Python framework for developers and researchers building systems where AI agents share work. The code uses the Apache 2.0 license.

Google ADK is an open-source AI agent framework for developers building applications that carry out multi-step tasks. You can run agents locally in Docker or on your own infrastructure, and connect them to locally running models through adapters. The framework is optimized for Gemini but supports other models and providers. Its Python repository uses the Apache 2.0 license.

Prime Agent is a local AI coding and research agent for developers and researchers whose tasks need to continue across terminal sessions. It runs commands and edits files in your project directory, while background sessions keep working after you disconnect. The code is open source under the MIT License. Model access uses a subscription or an API-key provider.

II Agent is a self-hosted AI agent for developers and teams who want an assistant that can research a topic, write software and carry out tasks through a browser or shell. It's a Python framework with a web interface, released under Apache 2.0, so you can inspect, fork and extend the code.

Magic Context is a context and memory plugin for developers working with coding agents in OpenCode, Pi, and OMP. Part of CortexKit, it keeps project knowledge across sessions and handles history compression in the background so context management doesn't interrupt ongoing work.

Alfred Black is a self-hosted AI agent for solo business owners and consultants who need help with inbox triage, follow-ups, and keeping track of ongoing work. It runs continuously on a Linux server through Docker, with a web dashboard and conversations through Telegram, Slack, email, or web chat.

agentchattr is a local chat server for developers who want multiple AI coding agents to work together in one conversation. Humans and agents can mention each other to prompt a response, so you don't have to carry messages between separate terminals. It runs on Windows, macOS and Linux, with a browser interface.

Acontext turns AI agent sessions into Markdown skill files that agents can reuse on later tasks. It's for developers who want agents to retain successful approaches, past mistakes, and user preferences in memory they can inspect and correct. The full stack can run on your own infrastructure, and a hosted cloud service is also available. It's open source under Apache 2.0.

Pi Boomerang is an extension for the Pi coding agent that reduces how much task history carries into later prompts. It's for developers whose bug fixes and refactoring jobs fill the conversation with file reads, edits and test output. After a task finishes, it replaces that history in future model context with a handoff summary. File changes stay on disk, and the full history remains accessible in Pi's session tree.

kodo coordinates installed coding agents so developers can leave a defined task running for hours. It runs locally on macOS, Linux and Windows and is open source under the MIT license. It's aimed at work with a clear goal that can progress without frequent human decisions.

Prompty is an MIT-licensed, open-source prompt format and developer toolkit for AI applications. It keeps a prompt's text, model settings, inputs, and tool definitions in one portable Markdown file. Developers can use the same file in VS Code and across Python, TypeScript, C#, and Rust runtimes.

OpenRath is an open-source Python runtime for developers building AI agent workflows that need to preserve the work behind an answer. Its central object is a session, which keeps conversation context, tool results, execution location and validation evidence together. That gives engineering and research teams a record they can inspect, branch, resume and compare.

Exo Agent Framework is a self-hosted framework for developers building long-running AI agents that can revise their own code, tools and prompts. Its exoharness foundation keeps agent history and resources separate from the logic that decides what the agent does next. The project is open source under the MIT license.

OpenHarness SDK is a TypeScript toolkit for developers building their own AI agents or coding assistants in the style of Claude Code. It runs in Node.js or edge runtimes and is open source under the MIT license. You control the application code; model calls use your chosen provider through Vercel AI SDK, including OpenAI, Anthropic, and Google.