[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-84140":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":13,"stars7d":15,"stars30d":15,"stars90d":14,"forks30d":14,"starsTrendScore":16,"compositeScore":17,"rankGlobal":9,"rankLanguage":9,"license":18,"archived":19,"fork":19,"defaultBranch":20,"hasWiki":21,"hasPages":19,"topics":22,"createdAt":9,"pushedAt":9,"updatedAt":23,"readmeContent":24,"aiSummary":9,"trendingCount":14,"starSnapshotCount":14,"syncStatus":12,"lastSyncTime":25,"discoverSource":26},84140,"Sibyl-Memory","Sibyl-Labs\u002FSibyl-Memory","Sibyl-Labs","Sibyl Memory Plugin for Hermes enables persistent memory across long time horizons, and enables relational context previously unavailable. Self-learning and auto-skill creation creates an agent that grows with you.  Local SQLite, structured tiers, no vector DB. SDK, CLI, MCP server, Hermes plugin.",null,"Python",79,2,3,0,7,13,1.43,"MIT License",false,"main",true,[],"2026-06-12 02:04:38","\u003Cdiv align=\"center\">\n\n```\n███████╗██╗██████╗ ██╗   ██╗██╗     \n██╔════╝██║██╔══██╗╚██╗ ██╔╝██║     \n███████╗██║██████╔╝ ╚████╔╝ ██║     \n╚════██║██║██╔══██╗  ╚██╔╝  ██║     \n███████║██║██████╔╝   ██║   ███████╗\n╚══════╝╚═╝╚═════╝    ╚═╝   ╚══════╝\n\n         M  E  M  O  R  Y\n```\n\n**agentic memory infrastructure · file-based · zero embeddings**\n\n[![PyPI · client](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fsibyl-memory-client?label=client&color=8a6a2a)](https:\u002F\u002Fpypi.org\u002Fproject\u002Fsibyl-memory-client\u002F)\n[![PyPI · cli](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fsibyl-memory-cli?label=cli&color=8a6a2a)](https:\u002F\u002Fpypi.org\u002Fproject\u002Fsibyl-memory-cli\u002F)\n[![PyPI · hermes](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fsibyl-memory-hermes?label=hermes&color=8a6a2a)](https:\u002F\u002Fpypi.org\u002Fproject\u002Fsibyl-memory-hermes\u002F)\n[![PyPI · mcp](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fsibyl-memory-mcp?label=mcp&color=8a6a2a)](https:\u002F\u002Fpypi.org\u002Fproject\u002Fsibyl-memory-mcp\u002F)\n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-15110a.svg)](.\u002FLICENSE)\n[![Python 3.10+](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython-3.10+-15110a.svg)](https:\u002F\u002Fwww.python.org\u002Fdownloads\u002F)\n[![LongMemEval](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLongMemEval-95.6%25%20%23%E2%80%832-2e6b3a.svg)](https:\u002F\u002Fblog.sibylcap.com\u002Flongmemeval-v2)\n\n\u003Csub>\u003Ci>built by an autonomous agent · sibyl labs llc\u003C\u002Fi>\u003C\u002Fsub>\n\n\u003C\u002Fdiv>\n\n---\n\n## What this is\n\nFour PyPI packages, one schema family, one architecture.\n\n`sibyl-memory-client` is a local-first agentic memory SDK. SQLite-backed, five-tier hierarchical schema, FTS5 search, multi-tenant by design. No vector database. No embedding model. No external retrieval service. The memory lives on the agent's machine; the substrate is a single file on disk.\n\nThe other three packages ride on top: `sibyl-memory-cli` for activation and tier management, `sibyl-memory-hermes` for Hermes Agent integration, and `sibyl-memory-mcp` for any MCP-compatible client (Claude Code, Codex, Cursor, Continue).\n\nThe architecture was benchmarked publicly on [LongMemEval Oracle](https:\u002F\u002Fblog.sibylcap.com\u002Flongmemeval-v2) (ICLR 2025, University of Michigan, 500 questions) and placed **#2 overall at 95.6%**, tied with Chronos (PwC), beating Mastra, MemMachine, Hindsight, Mem0, Supermemory, Zep, and the Oracle baseline. It is the only file-based system in the top tier: running on a single 4 vCPU \u002F 16 GB box, no vector infrastructure, no embedding fees.\n\nThis is the entire stack as it ships to production agents today.\n\n---\n\n## Packages\n\n| Package | PyPI | Description |\n|---|---|---|\n| [`sibyl-memory-client`](.\u002Fsibyl-memory-client) | [![PyPI](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fsibyl-memory-client)](https:\u002F\u002Fpypi.org\u002Fproject\u002Fsibyl-memory-client\u002F) | Local-first agentic memory SDK. SQLite-backed five-tier hierarchical schema, FTS5 search, multi-tenant, with self-learning skill detection and local memory linter. Foundation of the plugin family. |\n| [`sibyl-memory-cli`](.\u002Fsibyl-memory-cli) | [![PyPI](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fsibyl-memory-cli)](https:\u002F\u002Fpypi.org\u002Fproject\u002Fsibyl-memory-cli\u002F) | Command-line interface. `sibyl init` activates, `sibyl upgrade` runs the staker \u002F subscription flow, `sibyl status` shows current tier and DB stats, `sibyl whoami`, `sibyl devices`. |\n| [`sibyl-memory-hermes`](.\u002Fsibyl-memory-hermes) | [![PyPI](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fsibyl-memory-hermes)](https:\u002F\u002Fpypi.org\u002Fproject\u002Fsibyl-memory-hermes\u002F) | Bundled memory payload for Hermes Agent v0.13+ (and any other Python orchestration that wants direct SDK access). |\n| [`sibyl-memory-mcp`](.\u002Fsibyl-memory-mcp) | [![PyPI](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fsibyl-memory-mcp)](https:\u002F\u002Fpypi.org\u002Fproject\u002Fsibyl-memory-mcp\u002F) | MCP server. Wraps the local SQLite + FTS5 memory engine and exposes it to MCP-compatible agents (Claude Code, Codex, Cursor, Continue, anything that speaks MCP). |\n\n---\n\n## Install\n\n```bash\npip install sibyl-memory-cli\nsibyl init\n```\n\n`sibyl init` opens a browser to activate your account, binds your wallet or email, and writes credentials to `~\u002F.sibyl-memory\u002Fcredentials.json`. Free tier is the default; staker and subscription tiers unlock self-learning, the memory linter, and remove the local cap.\n\nFor direct SDK use:\n\n```bash\npip install sibyl-memory-client\n```\n\nFor Hermes integration:\n\n```bash\npip install sibyl-memory-hermes\nsibyl-memory-hermes install-plugin\n# then edit ~\u002F.hermes\u002Fconfig.yaml:\n#   memory:\n#     provider: sibyl\n```\n\nFor MCP (Claude Code, Codex, Cursor, Continue, ...):\n\n```bash\npip install sibyl-memory-mcp\n# then point your MCP client at the server entry point.\n```\n\nFull documentation at [docs.sibyllabs.org\u002Fmemory](https:\u002F\u002Fdocs.sibyllabs.org\u002Fmemory\u002F).\n\n---\n\n## Architecture\n\n```\n┌─────────────────────────────────────────────────────────┐\n│  sibyl-memory-cli       sibyl-memory-mcp                │\n│  ┌──────────────┐       ┌──────────────┐                │\n│  │ sibyl init   │       │ MCP server   │                │\n│  │ sibyl status │       │ (stdio)      │                │\n│  │ sibyl whoami │       └──────┬───────┘                │\n│  └──────┬───────┘              │                        │\n│         │     sibyl-memory-hermes                       │\n│         │     ┌──────────────┐                          │\n│         │     │ Hermes hook  │                          │\n│         │     └──────┬───────┘                          │\n│         │            │                                  │\n│         └──────┬─────┘                                  │\n│                ▼                                        │\n│         sibyl-memory-client (SDK)                       │\n│         ┌────────────────────────┐                      │\n│         │ SQLite + FTS5          │                      │\n│         │ 5-tier schema          │                      │\n│         │ self-learning skills   │                      │\n│         │ multi-tenant           │                      │\n│         └────────────────────────┘                      │\n└─────────────────────────────────────────────────────────┘\n```\n\nEach package has its own `README.md` and `CHANGELOG.md` for the detail.\n\nThe five tiers, in case you're curious:\n\n```\n  HOT        state\u002F        live working state, rewritten in place\n  WARM       entities\u002F     single source of truth per (category, name)\n  COLD       journal\u002F      append-only event log\n  REFERENCE  reference\u002F    static knowledge, rarely changes\n  ARCHIVE    archive\u002F      retired entities, kept for audit\n```\n\nRule 43 (single source of truth per entity) is enforced at the schema level via a `UNIQUE (tenant_id, category, name)` constraint, not just a convention in the application code. Drift is impossible by construction.\n\n---\n\n## Provenance\n\nBuilt by [SIBYL](https:\u002F\u002Fx.com\u002Fsibylcap), the autonomous agent operating at [Sibyl Labs LLC](https:\u002F\u002Fsibyllabs.org).\n\nThe agent has been operating in production since February 2026, ships code daily, holds an on-chain identity on Base (ERC-8004 agent ID 20880), runs an autonomous trading engine, an on-chain messaging protocol, an x402 payment rail, a token-gated chat demo, an advisory dashboard, and this memory product family. Everything verifiable on-chain.\n\nMemory architecture is the proven core. Sibyl Labs LLC owns the IP, signs contracts, and holds the legal wrapper around the agent's work. The work itself is shipped by the agent, in sessions, through the operator (`@tradingtulips`). The PyPI releases, the CLI, the SDK, the CLI banner above: all of it is autonomous agent output.\n\nThe on-chain record is the resume. This repository is one chapter of it.\n\n---\n\n## License\n\nMIT. See [LICENSE](.\u002FLICENSE).\n\nCopyright (c) 2026 Sibyl Labs LLC.\n","2026-06-11 04:12:22","CREATED_QUERY"]