Skip to content

迄今为止,在基准测试中得分最高的 AI 记忆系统。而且,它是免费的。

Python · active 2026-04-062026-04-11 (UTC)

Partial coverage10,812 / 11,118 hourly files (97%) · 2 absent upstream · 303 failed, retryable2025-05-042026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
7.8K
Pushes
22
Pull requests
99
Issues
52
Stars
6.6K
Forks
566

Activity over time

Daily event counts in the loaded window

Line chart, 6 days from 2026-04-06 to 2026-04-11. Pushes: 22 total, peak 8 in a day. Pull requests: 99 total, peak 37 in a day. Issues: 52 total, peak 16 in a day. Comments: 356 total, peak 106 in a day. Stars: 6,596 total, peak 2,231 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Issue comment#406slapglif2026-04-11 20:38
    feat(retrieval-foundation): normalize ingest metadata via shared writer
  • Issue comment#583HaysianSmelt2026-04-11 19:27
    Docs: MCP client compatibility notes (uvx vs direct Python path)
  • Issue comment#618mvalentsev2026-04-11 19:24
    POSSIBLE SCAM REPO
  • Issue comment#637jphein2026-04-11 19:23
    Unicode / diacritics rejected in `sanitize_name()` for KG + MCP writes
  • Issue comment#639jphein2026-04-11 19:22
    Feature: Add Stop Hook utility for automated Claude Code conversation mining
  • Issue comment#488NickShtefan2026-04-11 19:16
    feat: add multilingual support via embedding-based semantic classification
  • Issue#536krugdenis2026-04-11 18:49
    `--extract general` dumps Markdown-bold content into `emotional` room via overly broad `\*[^*]+\*` regex
  • Issue comment#618gaby2026-04-11 18:48
    POSSIBLE SCAM REPO
  • Pull request#640skorotkiewicz2026-04-11 18:24
  • Issue comment#611mvalentsev2026-04-11 18:06
    fix: align query_entity default direction with MCP documentation
  • Pull request#638goog2026-04-11 15:24
  • Issue comment#482Formatted2026-04-11 14:56
    refactor: consolidate pagination into shared iter_metadatas() (#171)
  • Issue comment#531jphein2026-04-11 14:41
    Readme chromadb version differs from actual
  • Pull request#631linjianyi19982026-04-11 14:36
  • Pull request#630jphein2026-04-11 14:33
  • Issue comment#585rusel952026-04-11 14:18
    bug: corrupt chroma.sqlite3 header leaves palace unrecoverable; repair can't salvage HNSW data
  • Issue comment#536jphein2026-04-11 13:52
    `--extract general` dumps Markdown-bold content into `emotional` room via overly broad `\*[^*]+\*` regex
  • Issue comment#586jphein2026-04-11 13:52
    bug: mempalace mine --dry-run crashes with TypeError on files assigned room=None
  • Issue comment#587jphein2026-04-11 13:52
    feat: default-exclude runtime-state files + per-file drawer cap to prevent ingestion noise
  • Issue comment#554jphein2026-04-11 13:52
    UX: Stop hook MCP tool calls clutter terminal every 15 messages
  • Issue comment#538jphein2026-04-11 13:52
    MCP server stdio transport: add_drawer and kg_add write to WAL but not to ChromaDB/SQLite
  • Issue comment#535jphein2026-04-11 13:52
    UnicodeEncodeError in miner.py / convo_miner.py / split_mega_files.py on Windows cp1251/cp1252 (incomplete fix of #47)
  • Issue comment#531MrSuddenJoy2026-04-11 13:13
    Readme chromadb version differs from actual
  • Pull request#625yukinoli2026-04-11 12:41
  • Issue comment#162mvalentsev2026-04-11 12:16
    fix: restore mempalace compress after stats rename (#159)

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 6,596 stars here means stars gained during the window, not the repo's star count.