Skip to main content
AdOpenFree logoPromote your productReach more potential users and drive product growth and revenue.Advertise

Tools tagged with "Context Management"

Favicon of DeepSeek Harness

DeepSeek Harness

Free ListingStars: 237.5K

Everything is a plugin.

Agent Frameworks

DeepSeek Harness (dsh) is an open-source agent harness in developer preview. Every agent capability is implemented as a composable Cordis plugin for models, tools, skills, sessions, sandboxes, storage, loops, scheduling, and the UI.

Favicon of Caveman

Caveman

Free ListingStars: 113.1K

Make AI agents say less and read less.

Coding Agents

Caveman is an open-source response skill and local CLI proxy for coding agents. It shortens answers and compresses inputs like logs, JSON, CSV, and test output while keeping code, commands, paths, and error messages exact.

Favicon of claude-mem

claude-mem

Free ListingStars: 101.6K

Persistent context across sessions for every agent

MCP Servers & Tool Connectors

Open-source persistent memory engine that captures agent session activity, compresses it with AI, and injects relevant context into future sessions across Claude Code, Codex, Gemini, OpenCode, and other supported tools.

Favicon of Model Context Protocol

Model Context Protocol

Free ListingStars: 90.6K

Open standard for connecting AI apps to external systems

MCP Servers & Tool Connectors

Model Context Protocol (MCP) is an open-source standard for connecting AI applications to external systems. It enables access to data sources, tools, and workflows. This repository offers reference MCP servers and SDK examples.

Favicon of Headroom

Headroom

Free ListingStars: 75.7K

Compress LLM context before it reaches the model

MCP Servers & Tool Connectors

Headroom is a context optimization layer for LLM applications. It compresses tool outputs, database results, file reads, logs, RAG results, and API responses before they reach the model, reducing tokens while keeping the same answers.

Favicon of Mem0

Mem0

Free ListingStars: 66K

AI memory that persists across sessions and agents

Agent Memory

Mem0 is a drop-in memory infrastructure for AI agents and apps, providing persistent context that enables continuous learning from past user interactions for enhanced intelligence and personalization.

Favicon of OpenViking

OpenViking

Free ListingStars: 38.7K

Open-source context database for AI agents

Vector Databases

OpenViking is an open-source context database for AI agents. It unifies agent memory, knowledge RAG, and skills, organizing context as a navigable filesystem for retrieval and reuse.

Favicon of Context Mode

Context Mode

Free ListingStars: 30.2K

The control plane between coding agents and models.

Agent Memory

Context Mode is a control plane between AI coding agents and model APIs. It folds tool output before the model reads it, archives full output, persists memory and skills across sessions, and enforces rules for commands and file reads.

Favicon of Repomix

Repomix

Free ListingStars: 29K

Pack your codebase into AI-friendly formats

Context Management

Repomix packages an entire codebase into a single AI-friendly file, making repository context easy to share with LLMs and AI tools for code reviews, refactoring, implementation planning, documentation, and project assistance.

Favicon of Elephant-Goldfish Model

Elephant-Goldfish Model

Free ListingStars: 18.6K

Design with context, review with fresh eyes

Coding Agents

EGM is an open-source plugin for AI assistants that helps teams draft plans with full project context, then have fresh reviewers who did not see the conversation identify missing or unclear details before implementation.

Favicon of LMCache

LMCache

Free ListingStars: 12.3K

KV cache management layer for scalable LLM inference

Context Management

LMCache is an open-source KV cache management layer for LLM inference that stores, compresses, searches, and reuses KV cache across GPU, CPU, local storage, and external backends to reduce repeated prefill and improve time-to-first-token.

Favicon of ai-memory

ai-memory

Free ListingStars: 9.7K

Long-term memory for AI coding agents

Agent Memory

A self-hosted long-term memory system for AI coding agent CLIs. It captures sessions into a git-backed Markdown wiki, shares project context across agents and machines, and supports typed handoffs between different harnesses.

Favicon of TokenEconomizer

TokenEconomizer

Free ListingStars: 5.9K

Experience-driven cost control for coding agents

Coding Agents

TokenEconomizer is a plugin that learns from prior coding-agent sessions in a repository to reduce costs by remembering repository facts, pruning unused tools, and intervening in failure loops without changing the agent.

Favicon of EAC-Desktop

EAC-Desktop

Free ListingStars: 3.1K

Open-source desktop workbench built on DeepSeek Harness

Personal & Desktop Assistants

EAC-Desktop (Embracing All Creation Desktop) is an open-source desktop workbench built on DeepSeek Harness for harmonious coexistence of hundreds of DSH plugins, with native windows, isolated environments, and bundled runtime resources.

Favicon of TrustGraph

TrustGraph

Free ListingStars: 2.8K

Business meaning in the graph, authority in the runtime

Guardrails & Content Moderation

TrustGraph is an open-source context graph platform with a deterministic agent runtime. It builds an ontology-grounded operating graph and checks AI agent actions against business meaning and evidence, returning allow, pause or deny.

Favicon of billion-context

billion-context

Free ListingStars: 1.7K

Context-compression plugin for long coding sessions

Context Management

billion-context is a context-compression plugin that lets agents work with small context windows, use about 5x fewer tokens, and sustain month-long single sessions handling billions of tokens.

Favicon of MCode Stack

MCode Stack

Free ListingStars: 0.2K

Open-source workflows and skills from the MiniMax Code team

Coding Agents

Open-source workflows and skills the MiniMax Code team uses to build MiniMax Code. Install individual skills or full stacks as plugins in MiniMax Code and compatible agents.

Favicon of Octop Memory

Octop Memory

Free ListingStars: 0.1K

Your intelligent partner that understands and grows with you

Agent Memory

Octop is Tencent's open-source, self-hostable intelligent collaboration partner for individuals and teams. It offers parallel digital assistants and optional Octop Memory for persistent, portable LLM-agent context on SQLite or PostgreSQL.

Ad
OpenFree logoPromote your product

Reach more potential users and drive product growth and revenue.

Advertise