Data / Repositories / Embeddings
Embeddings repositories on GitHub: 12 ranked by stars
12 public repositories tagged Embeddings are on GitHub, with 172,888 stars between them; 9 had a push in the last 30 days. Most are written in TypeScript (6), Rust (3), Go (1). The most starred: thedotmack/claude-mem (100,675), Tencent/WeKnora (33,958), InsForge/InsForge (13,115).
SpecStream is the live web data engine for teams and agents. It reads open-source repositories on GitHub and keeps what it reads, and this page groups that reading by topic. Ask for the repositories you track by topic, language, license or activity, and new ones and changes arrive in your sheet, CRM, Slack or agent.
Every repository, most starred first
| Repository | What it is | Language | Stars | Forks | License | Last push | Read |
|---|---|---|---|---|---|---|---|
| thedotmack/claude-mem | Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future… | TypeScript | 100,675 | 8,823 | Apache-2.0 | Oct 13 | Oct 14 |
| Tencent/WeKnora | Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki. | Go | 33,958 | 4,519 | Oct 14 | Oct 14 | |
| InsForge/InsForge | The all-in-one, open-source backend platform for agentic coding. InsForge gives your coding agent database, auth, storage, compute, hosting, and AI gateway to ship full-stack apps… | TypeScript | 13,115 | 1,222 | Apache-2.0 | Oct 13 | Oct 14 |
| MinishLab/semble | Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read | Python | 6,204 | 276 | MIT | Oct 11 | Oct 14 |
| Marker-Inc-Korea/AutoRAG | AutoRAG: Now your agent can find anything in your computer. It gets smarter if you are using it frequently. | TypeScript | 5,122 | 446 | Oct 10 | Oct 11 | |
| CaviraOSS/LongMemory | Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc. | TypeScript | 4,535 | 507 | Apache-2.0 | Sep 20 | Oct 14 |
| twinnydotdev/twinny | Open-source AI coding assistant for VS Code. Code completion, chat, edits and reviews with local or hosted models. Your models, your infrastructure. | TypeScript | 3,670 | 231 | MIT | Oct 12 | Oct 14 |
| giancarloerra/SocratiCode | Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level… | TypeScript | 3,335 | 430 | AGPL-3.0 | Oct 10 | Oct 14 |
| run-llama/semtools | Semantic search and document parsing tools for the command line | Rust | 1,874 | 144 | MIT | Mar 11 | Oct 11 |
| Govcraft/rust-docs-mcp-server | Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call. | Rust | 299 | 39 | MIT | Nov 24, 2025 | Oct 14 |
| major7apps/pensyve | Universal memory runtime for AI agents | Rust | 96 | 16 | Oct 8 | Oct 14 | |
| managedcode/MCPGateway | Searchable MCP and AITool gateway for .NET, built on Microsoft.Extensions.AI with embedding-based tool discovery, lexical fallback, and unified execution | C# | 5 | 0 | MIT | Oct 13 | Oct 14 |
By language
- TypeScript 6
- Rust 3
Related topics
- AI 7
- RAG 6
- LLM 6
- OpenAI 5
- Semantic search 5
- MCP 5
- AI agents 4
- AI memory 3
- Artificial intelligence 3
- Agents 3
- Ollama 3
- Vector search 3
Read from GitHub by SpecStream between October 11, 2026 and October 14, 2026; each row shows the day its repository was read. Stars and pushes change every day, and the GitHub page is the current one. Forks and archived repositories are left out.