A cheap, persistent codebase memory for Claude Code — so your agent stops re-reading the repo. A separate large-context model learns your codebase passively across sessions and answers via the asklivememory MCP tool instead of re-loading files; read-only, zero-config on a Claude subscription.
★not rated 7 2mo agoA
tokens not measured
originalApache-2.0
A cheap background model that watches your Claude Code session over its shoulder and, rarely, drops one short advisory into it — asynchronously, without ever blocking. It reads only the agent's emissions (29% of the transcript), never its tool results, so it is affordable to leave running for the whole session.
★not rated 2 2mo agoA
tokens not measured
originalApache-2.0
Run deterministic, .slang-driven multi-agent workflows inside Claude Code. A non-LLM state machine in an MCP server coordinates agents (via the Agent SDK); the top-level session triggers and observes runs.
★not rated 1 2mo agoA
tokens not measured
originalApache-2.0