Authorization notice. Semantix is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.
Who it is forAn engineer who runs a custom or self-hosted agent and wants its tools to read from the Semantix memory kernel.
The problemA custom agent starts every task without memory of earlier sessions, and rebuilding that memory by hand is slow.
The outcomeThe agent calls semantix_lookup to find relevant slices and semantix_inject to add them to context, falling back to its normal path on kernel error.
What you need first
- macOS or Linux on arm64 or amd64 for the one-line install
- A model provider account and API key, set up on the first run of semantix
- Go 1.26 or later only if you build from source
- A session transcript in JSONL format for the extract and verify steps
Steps
- Run the install command from the README to get the Semantix binaries, or build from source with
go build -o semantix ./cmd/semantix. - Read the tool schemas in agent-skill/tools/ and the hook notes in agent-skill/hooks/session-bypass.md.
- Register the semantix_lookup and semantix_inject schemas in your agent's tool list.
- Export a finished session and run
semantix extract --input session.jsonl --db .semantix/project.db --project demo.
Prompt for your agent
Using the Gnosil/semantix repo, register the semantix_lookup and semantix_inject tool schemas from agent-skill/tools/ in <agent>. Run one task that should match an extracted session and report which slices the lookup returned. Verify that the agent still completes the task when the semantix binary is removed, since the README says the kernel fails open.
Caveat. The README describes the two tool schemas and hooks but does not give their full parameter lists, so read agent-skill/tools/ before wiring them in.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page