🏆 #3,052 overall#694 of 1,507 in Search & Retrieval

lovstudio /Ataru

High-performance AI memory retrieval for local agent history — a Rust search core (SDK / API / JSON CLI) plus a desktop GUI. Tantivy + Jieba keyword search, optional semantic recall, stable Turn/Run/Session/Project IDs.

$ git clone https://github.com/lovstudio/Ataru.git
GitHub social preview for lovstudio/Ataru
Stars
362
362
This week
+1 ★
+2 this month
Forks
40
40
Language
Rust
License
Apache-2.0
Created
Dec 10, 2025
0.9 years old
Last push
Aug 24, 2026

Stars, last 30 days

Oct 15, 2026 → Nov 16, 2026
★ 359▲ +3★ 362

Categories

GitHub topics

More in Search & Retrieval

Search & Retrieval

MaxFreedomPollard/Compartment🔥 active

Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Superior memory creation, storage and retrieval.

PythonApache-2.0updated Nov 14, 2026
GitHub ↗★ 569⑂ 8
Search & Retrieval

liliang-cn/cortexdb🔥 active

Local-first AI agent memory with a knowledge graph, ontology constraints, and traceable reasoning—all in one SQLite file.

GoMITupdated Nov 16, 2026
GitHub ↗★ 520⑂ 35
Search & Retrieval

codecoradev/uteke🔥 active

▲ +5 ★ this week

Long-term memory for AI agents (MCP). One Rust binary, offline, 98.2% recall@5 on LongMemEval-S. Works with Claude Code, Cursor, Codex. Self-host free or use Uteke Cloud.

RustApache-2.0updated Nov 16, 2026
GitHub ↗★ 289⑂ 31
Search & Retrieval

linggen/linggen-memory🔥 active

Local-first semantic memory for AI assistants — one store your preferences, decisions and gotchas follow you into, across Claude Code, Codex, Cursor and Zed.

RustMITupdated Nov 16, 2026
GitHub ↗★ 111⑂ 6
Search & Retrieval

xerj-org/xerj🔥 active

AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.

RustApache-2.0updated Nov 16, 2026
GitHub ↗★ 19.1K⑂ 1.4K
Search & Retrieval

MemoriLabs/Memori

Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

PythonOtherupdated Oct 3, 2026
GitHub ↗★ 17.6K⑂ 4K

Data from GitHub · snapshot Nov 16, 2026