TinySuiteChangelog
A running record of released changes across every TinySuite project.
What changed Add the list memories MCP tool for newest first, filterable, paginated memory previews. Add the get memory MCP tool to retrieve a memory by full ID or short reference. Keep the FastAPI endpoints aligned w…
Read on GitHubTinySearch v0.6.2 TinySearch v0.6.2 makes web research more focused and efficient, with smarter handling of overlapping crawl evidence and a set of quality and performance optimizations. What's changed Semantic dedupl…
Read on GitHubFull Changelog : https://github.com/TinySuiteHQ/TinySearch/compare/v0.6.0...v0.6.1
Read on GitHubWhat's Changed feat: add optional external browser via Chrome DevTools Protocol by @MarcellM01 in https://github.com/TinySuiteHQ/TinySearch/pull/48 Feat/scrape link discovery by @MarcellM01 in https://github.com/TinyS…
Read on GitHubWhat’s new Add profile memories with global access across sessions and a dedicated profile token budget. Add newest first recent recall when no query is supplied, with bounded token aware results. Add memory supersess…
Read on GitHubWhat’s new Expose stable 12 character memory refs from save and recall, so delete memory no longer requires copying a full UUID. Accept either a short ref or full id for deletion, with explicit handling for ambiguous…
Read on GitHubTinySearch v0.5.1 makes batched scraping more efficient and predictable. Reuses one browser across concurrent scrape urls items. Bounds document download timeouts and removes the unused crawl helper. Keeps local uv lo…
Read on GitHubWhat’s new Add delete memory(memory id) across the Python API, MCP server, and FastAPI server, including clear not found handling. Document the new deletion workflow. Stop tracking uv.lock; it is now ignored.
Read on GitHubFull Changelog : https://github.com/TinySuiteHQ/TinyContext/compare/v0.2.1...v0.2.2
Read on GitHubTinySearch v0.5.0 TinySearch 0.5.0 makes web retrieval simpler and more useful for MCP agents. Highlights Let agents formulate retrieval queries. Agents can now rewrite, clarify, translate, narrow, spell correct, and…
Read on GitHubFull Changelog : https://github.com/TinySuiteHQ/TinyContext/compare/v0.2.0...v0.2.1
Read on GitHubWhat's Changed Feat/direct xml mcp responses by @MarcellM01 in https://github.com/TinySuiteHQ/TinySearch/pull/43 Full Changelog : https://github.com/TinySuiteHQ/TinySearch/compare/v0.4.2...v0.4.3
Read on GitHubHighlights Added hybrid BM25 + dense retrieval using SQLite FTS5 and sqlite vec. Added structured recall context, relevance labels, and configurable RRF cutoffs. Added benchmark results and methodology to the README.…
Read on GitHubWhat's new Strip nav, header, footer, and aside boilerplate before markdown generation, improving evidence quality and reducing wasted tokens. Harden Docker delivery with Trivy configuration, repository secret, image…
Read on GitHubTinyContext v0.1.0 The first public release of TinyContext, a token light local memory layer for AI agents. TinyContext stores concise memories and embeddings in SQLite, combines lexical and semantic retrieval, and re…
Read on GitHubWhat's Changed Project repository moved to the TinySuiteHQ GitHub org — all package metadata (server.json, pyproject.toml, Dockerfile, README) now references github.com/TinySuiteHQ/TinySearch. CI: removed a redundant…
Read on GitHubTinySearch 0.4.0 makes local first, token efficient web research easier to install, run, and integrate. Search, crawling, embeddings, and hybrid reranking turn webpages into compact, source grounded evidence without r…
Read on GitHubFull Changelog : https://github.com/MarcellM01/TinySearch/compare/v0.3.1...v0.3.2
Read on GitHubWhat's Changed Harden scraping and parsing against ReDoS and bump vulnerable dependendencies by @MarcellM01 in https://github.com/MarcellM01/TinySearch/pull/17 Full Changelog : https://github.com/MarcellM01/TinySearch…
Read on GitHubTinySearch v0.3.0 Focused release for agent workflows: read a known URL directly, and fetch the current UTC date/time on demand. What's new Direct URL inspection scrape url / POST /scrape When you already have a URL,…
Read on GitHub