CalibratedDecisions.

Repo · Context & memory

jevmem (illescasDaniel)

Agent long-term memory via TypeSafe Jev typed decisions (MCP, Claude Code hooks, CLI, SQLite)—no generative LLM in the memory loop (MIT; distinct…

Open github.com ↗

From the repository

Long-term memory for AI agents driven by Jev (System One) decisions: no generative LLM in the loop. MCP server, Claude Code hooks, CLI, Python library.

How builders describe it

Agent long-term memory via TypeSafe Jev typed decisions (MCP, Claude Code hooks, CLI, SQLite)—no generative LLM in the memory loop (MIT; distinct from libingzheren/Jev-Mem).

The decision Jev makes

Keep or discard a tool result, or answer whether a stopping condition is met.

Where it fits

Agents drown in their own context. These projects use Jev to decide what to keep, what to drop and when a loop is actually finished. All 117 context & memory projects →

Related projects