Manages your agent's context window so it reads only what matters. 164x fewer tokens on large codebases.
Auto-detects your runtime. One command to configure MCP servers.
Auto-detects runtimes, configures MCP servers, starts the daemon.
Your AI agent calls get_context with an action: plan, inspect, edit.
Returns only what matters — repo anchors, focus sets, coverage data.
Builds a structural map of your codebase — files, symbols, dependencies — so the agent navigates directly to what matters.
Ingests test coverage data to show which lines are tested vs untested. Agents know exactly where to add tests.
Each response stays within a configurable token budget. No more blowing through context windows on a single file read.
Agents mark files and symbols as "in focus." Packet28 tracks what the agent cares about across tool calls.
The packet28d daemon persists state across agent sessions. Start, stop, resume — your context survives restarts.
One setup command detects Claude Code, Cursor, Codex, and more. Configures MCP servers for each automatically.
Tested on Apache Commons Lang — 534 Java files, 12MB.