Back to directory

Semantix

A cross-session memory kernel for coding agents that extracts reusable knowledge from finished sessions and injects it into new ones, either as a standalone coding agent or attached to an agent already in use.

Semantix

Semantix addresses two related problems: a coding agent loses its context entirely when a session ends, and a provider's prompt cache only helps when a new prompt is byte-identical to an earlier one, so a single edit near the start invalidates the cached prefix. It extracts reusable slices, such as task patterns, project knowledge, tool sequences and verified results, from finished sessions into a local scored library, then retrieves, injects and verifies relevant slices in later sessions.

It can be used two ways: as semantix-agent, a complete command-line coding agent shipping with the memory kernel built in and provider presets for around fifty endpoints; or as a standalone kernel attached to an agent already in use, through an installable Claude Code skill, two tool schemas registered with a custom agent, or an OpenAI-compatible gateway that needs no code change. The kernel fails open, so the host agent falls back to its normal path if the kernel errors.

It installs with a single shell script on macOS and Linux.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.