The "sqlite" topic on GitHub groups 57 open-source projects in the DeepSeek Harness (DSH) ecosystem, led by layerfs with 2.7k GitHub stars. layerfs — Ephemeral Workspaces, durable shared history. Every project here is indexed by DSH Universe with live GitHub data — stars, activity and install status — so you can compare and install directly.
Ephemeral Workspaces, durable shared history. LayerFS gives every agent a complete, writable filesystem Workspace over shared committed history, without copying the base. Agents work in parallel, commit what changed as deduplicated checkpoints, then branch, rewind or merge. Try it with LayerFS × DSH.
Local long-term memory for Hermes, Codex, Claude Code, WorkBuddy and dsh agents: one SQLite store, source-backed recall, and tools to inspect, correct or delete what is remembered.
Your AI forgets every session. Give it a memory it can trust: local-first, review-gated agent memory — one SQLite vault for DSH, Claude Code, Codex, Cursor and any MCP client, with an immutable audit log and a token ledger. Open source, self-hosted, no cloud.
Give DeepSeek Harness cross-session long-term memory: the AI automatically remembers who you are, your projects and preferences, new sessions come with the background, personal and work memories are automatically kept separate without interfering, zero-config and seamless | Long-term memory for DeepSeek Harness: the AI remembers who you are, your projects and preferences across sessions, keeps personal and work memories separate, zero-config.
Retrieved ≠ injected: CBDC-gated memory for DeepSeek Harness — decides how memory is USED (use/verify/ignore + feedback learning + audit), not just stored
Recover deleted/corrupted dsh session logs and memory store from the raw disk — battle-tested recovery toolkit for DeepSeek Harness. Recover deleted or corrupted dsh session logs (session.jsonl.zstd) and memory (memory.db) from the raw disk — battle-tested recovery toolkit for DeepSeek Harness.
Token Check · Token management: token attention management panel for DeepSeek Harness (DSH) — records token usage and cost by task/day/week/month (hit/miss/output/reasoning), supports DeepSeek peak/off-peak pricing, and advises when to switch conversations or write a hand-off.
Local knowledge base for DeepSeek Harness: zero-dependency SQLite FTS5 index for markdown/text/code/web pages, source-cited retrieval, session experience library, interactive kbquery Web panel + knowledge galaxy.
Persistent scheduler for DeepSeek Harness: cross-restart reminders + scheduled jobs with dual remind/job actions, built on schedule-core. Every claim carries an experiment number.
Durable agent runs for local fleets, built on the DeepSeek Harness (dsh). Streamlined Orchestra rewrite: one execution path, stdlib Python, SQLite, three-file console.
Open-source, local-first envelope messaging for DeepSeek Harness: a TypeScript node, human-first inbox, explainable collaborator discovery, and bounded LAN recovery.
Office file processing and token-saving workflow. Three unique conventions — Excel goes entirely through SQLite (import → SQL query → export report); Word drafts go Markdown → docx (pandoc) then fine typography; PPT auto-selects scenario layouts by purpose and enforces official-document review before generation. Interactive grouped questions by default, executes only after confirming the checklist.
Layered long-term memory for coding agents: decaying episodic recall (L2), a provenance-tracking semantic graph (L3), and budgeted procedural skills (L4) in one embedded SQLite file. Deterministic retrieval, no model calls, no server. Ships a DeepSeek Harness plugin.
DeepSeek Harness plugin: a project task board kept with the project as a queryable SQLite file, with a kanban/list view in the Web Client, model-facing task tools, and cards you can dispatch to the agent as background jobs.