Trunkate AI

Semantically optimizes context history and large text blocks via the Trunkate AI API. Includes proactive context pruning hooks for automated token management.

This skill will read your OpenClaw session history file and send a filtered version to Trunkate's API (https://api.trunkate.ai) using the TRUNKATE_API_KEY you provide. That behavior is exactly what the skill claims to do, but it means potentially sensitive conversation content will leave your machine unless it is reliably redacted. The authors include a local redaction step and mechanisms for marking blocks as private ([PRIVATE] or [KEEP]), but redaction is based on regex heuristics (which can have false negatives and false positives). Before installing: 1) Confirm you trust trunkate.ai and are comfortable sending session history to an external service. 2) Avoid placing highly sensitive secrets in history, or explicitly mark them with [PRIVATE] / [KEEP]. 3) Review and test the redaction logic on representative histories to see whether it removes the kinds of secrets you care about. 4) If you do not want automatic transmissions before every LLM call, do not enable the PreRequest hook (or raise TRUNKATE_THRESHOLD). 5) Protect your TRUNKATE_API_KEY like any other secret and monitor API key usage for unexpected calls.

Type: OpenClaw Skill Name: trunkate Version: 0.31.0 The Trunkate AI skill provides semantic context optimization by sending session history to an external API (api.trunkate.ai) for pruning. While it transmits data externally, it is transparent about this behavior and includes robust local privacy protections in `scripts/activator.py`, which uses regex to redact secrets, system instructions, and user-defined `[PRIVATE]` blocks before transmission. The implementation follows security best practices, such as whitelisting environment variables in `hooks/openclaw/pre_request.py` to prevent accidental exfiltration of unrelated workspace credentials.