Haoran2099/dsh-focal

Haoran2099★ 0JavaScriptLast synced: 2026-08-14

Open on GitHub

Privacy-first task memory and adaptive local desktop observation for DeepSeek Harness

README excerpt

FOCAL for DeepSeek Harness FOCAL is an experimental, privacy-first memory plugin for DeepSeek Harness. It filters an agent session into task-isolated memories and injects only the active task's bounded context into later model requests. This is the DSH adaptation of FOCAL: Filtered On-device Continuous Activity Logging for Efficient Personal Desktop Summarization. The paper reproduction code remains in Haoran2099/focal . Status - Plugin version: v0.1.1 - DSH compatibility: 0.1.0-rc.6 - Verified against official commit 47f943859bef60e4160492346772ded9b24f765a - Clean-install and Host-load tested with the official 0.1.0-rc.6 CLI - Host plugin only; no Web UI extension yet DeepSeek Harness is currently a developer preview and warns that compatibility- breaking changes will occur. This package pins the supported DSH interfaces intentionally. Install Install directly from the tagged GitHub source. The package is plain ESM and has no install-time build script. Use --profile headless instead to add FOCAL to one-shot CLI runs. Remove it with: What it does - Observes committed session/event records. - Routes direct user messages into task-isolated memories using a small, deterministic simil…

View full README on GitHub →
Agentsagent-memorydeepseek-harnessdesktop-observationdsh-pluginfocallocal-firstagent

Category