Skip to content

Releases: ghostapp-ai/ghost

v0.14.2

27 Feb 19:14

Choose a tag to compare

0.14.2 (2026-02-27)

🐛 Bug Fixes

  • update version to 0.14.1 and improve error handling in various modules (ae4c99c)

v0.14.1

24 Feb 00:52

Choose a tag to compare

0.14.1 (2026-02-24)

🐛 Bug Fixes

  • route frontend errors to backend log buffer and add DebugPanel copy-to-clipboard (#14) (f42f891)

v0.14.0

22 Feb 01:02

Choose a tag to compare

0.14.0 (2026-02-22)

🚀 Features

  • embeddings: implement deferred loading for AI embedding engine (3ffb11e)

🐛 Bug Fixes

  • search: install TLS crypto provider in test_hybrid_search (0da91bb)

📚 Documentation

  • website: auto-sync content from source files [skip ci] (38230af)

v0.13.5

21 Feb 19:12

Choose a tag to compare

0.13.5 (2026-02-21)

🐛 Bug Fixes

  • chat: add CPU fallback when GPU model loading fails (e49ceb3)
  • inference: prefer discrete GPU over integrated in detection (b0ec1fb)
  • mcp: detect Ghost-managed runtimes and suppress terminal windows (7eb4ae7)

♻️ Code Refactoring

  • ui: make Ghost a normal desktop app with smart welcome (54d77f8)

v0.13.4

21 Feb 17:09

Choose a tag to compare

0.13.4 (2026-02-21)

🐛 Bug Fixes

  • ci: shorten Windows build path to fix MAX_PATH C1041 error (67ab4e0)

v0.13.3

21 Feb 16:48

Choose a tag to compare

0.13.3 (2026-02-21)

🐛 Bug Fixes

v0.13.2

21 Feb 16:29

Choose a tag to compare

0.13.2 (2026-02-21)

🐛 Bug Fixes

  • ci: replace /MP /FS with /Z7 to eliminate PDB race on Windows (2445fed)

v0.13.1

21 Feb 16:05

Choose a tag to compare

0.13.1 (2026-02-21)

🐛 Bug Fixes

  • ci: add /FS flag to Windows MSVC build to prevent PDB conflicts (ad5714d)

v0.13.0

21 Feb 15:41

Choose a tag to compare

0.13.0 (2026-02-21)

🚀 Features

  • chat: add hardware-adaptive inference configuration (b67338e)
  • chat: add Qwen3 model family with thinking mode support (fdb2dfa)
  • db: add sqlite-vec partition keys and filtered vector search (d7e0230)
  • frontend: runtime bootstrap UI, AI tool discovery, and drag fix (db58a10)
  • frontend: sync types with Qwen3 backend, expand AG-UI + A2UI rendering (cd15e29)
  • mcp: integrate Official MCP Registry (6,000+ servers) (336ffb1)
  • protocols: add zero-config runtime bootstrap system (af027f3)
  • protocols: expand AG-UI to 30+ events and add A2A agent card (493a4da)

🐛 Bug Fixes

  • ci: resolve 3 clippy errors in runtime_bootstrap tests (ca20399)
  • resolve clippy dead_code warnings and doc indentation (2187d09)

⚡ Performance

  • add dist build profile and reduce re-index interval to 60min (c66cc0d)
  • embeddings: real tensor batching + GPU device selection (ce6cca6)

📚 Documentation

  • update CLAUDE and ROADMAP files for clarity and accuracy; bump ghost version to 0.12.0 (2b7827a)
  • update core documents for Qwen3, sqlite-vec, and A2A additions (5c0b7b1)
  • update README, ROADMAP, and CLAUDE.md for runtime bootstrap (03e2cd2)
  • website: auto-sync content from source files [skip ci] (ad7284d)
  • website: auto-sync content from source files [skip ci] (103b362)

v0.12.0

21 Feb 00:44

Choose a tag to compare

0.12.0 (2026-02-21)

🚀 Features

  • mcp: add curated MCP tool catalog with one-click install (8d54189)

🐛 Bug Fixes

  • agent: make test_agent_run_emits_events robust for both CI and local (f955c25)
  • deps: update ghost package version to 0.11.2 (32df794)
  • inference: chunked batch prefill for prompts exceeding BATCH_SIZE (397743b)

♻️ Code Refactoring

  • mcp: integrate McpAppStore into Settings MCP tab (a10c58e)

📚 Documentation

  • seo: position Ghost as complete 2026 agent protocol stack (6a06697)
  • update core documents for MCP catalog and chunked prefill fix (195d29f)
  • website: auto-sync content from source files [skip ci] (800e850)