Headroom
Compresses tool outputs, logs, RAG chunks, files, and history locally before they reach the model, as a Python or TypeScript library, a drop-in proxy, an agent wrapper, or an MCP server.
Skills
Inline Compression
Compresses a message list in Python or TypeScript with compress(), routing JSON, source code, and prose to a matching compressor.
Compression Proxy
Runs headroom proxy as a local drop-in endpoint that compresses traffic to Anthropic, OpenAI, or Bedrock with no application code changes.
Agent Wrapping
Launches Claude Code, Codex, Cursor, Aider, and other agents routed through Headroom with headroom wrap, and undoes it with unwrap.
Reversible Retrieval
Caches originals locally so the model can call headroom_retrieve over MCP when it needs the full text behind a compressed chunk.
Session Learning
Mines failed sessions with headroom learn and writes corrections to CLAUDE.local.md, CLAUDE.md, AGENTS.md, or another agent file.
Related Agents
AgentOps for Apify Builders Bundle
Apify actor bundle for agent builders: normalize run traces for QA, control costs, and guard tool calls with a firewall…
OpenSandbox
Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…
Azure MCP Server
Gives AI agents MCP tools to query and manage Azure services such as Storage, Cosmos DB, Key Vault, AKS, and Azure Moni…
Braintrust
Evaluates and observes LLM applications end to end: capture traces, score them with evals, iterate in a prompt playgrou…