dify
MCPNOASSERTION
Open-source LLM app development platform for building AI workflows, RAG pipelines, and agents.
153k·LLM Ops·Open source
headroom
MCPOpen sourceOpen-source context compression layer for AI agents, cutting tokens 60-95% for JSON and 15-20% for coding.
67kApache-2.0
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Pros
- +Significant token reduction (60-95% for JSON, 15-20% for coding agents)
- +Multiple integration modes: library, proxy, MCP server, agent wrap
- +Reversible compression with local caching (CCR)
- +Cross-agent memory and learning from failed sessions
Cons
- −Requires setup and configuration for different agents
- −May add latency due to compression processing
- −Dependent on model quality for text compression (Kompress-v2-base)
Target audience: Developers building AI agents or applications that need to reduce token usage and costs while maintaining answer quality.
Related tools
Other open-source tools that share tags with headroom.
open-webui
MCPNOASSERTION
Self-hosted AI platform with chat UI, RAG, plugins, and multi-model support.
150k·Self-Hosted AI·Open source
Alternative to
worldmonitor
MCPAGPL-3.0
Open-source real-time global intelligence dashboard with AI news aggregation, geopolitical monitoring, and infrastructur
83k·MCP Servers·Open source
Alternative to
mindshub
MCPMIT
Open-source unified workspace to delegate projects to AI agents, route models, and publish artifacts.
40k·AI Agents·Open source
UI-TARS-desktop
MCPApache-2.0
Open-source multimodal AI agent stack with GUI automation, CLI, and desktop app.
39k·AI Agents·Open source
WrenAI
MCPNOASSERTION
Open-source generative BI engine for AI agents: governed text-to-SQL, semantic layer, and dashboard deployment across 22
17k·LLM Ops·Open source