{"id":46082625,"url":"https://github.com/anaslimem/cortexadb","last_synced_at":"2026-04-17T00:02:06.208Z","repository":{"id":340624148,"uuid":"1163315069","full_name":"anaslimem/CortexaDB","owner":"anaslimem","description":"It is a simple, fast, and hard-durable embedded database designed specifically for AI agent memory. It provides a single-file-like experience (no server required) but with native support for vectors, graphs, and temporal search.","archived":false,"fork":false,"pushed_at":"2026-03-17T00:07:39.000Z","size":1077,"stargazers_count":27,"open_issues_count":0,"forks_count":2,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-17T10:49:44.108Z","etag":null,"topics":["agentic-memory","ai-agents","graph-database","python","rust","vector-database"],"latest_commit_sha":null,"homepage":"https://cortexa-db.vercel.app","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/anaslimem.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE-APACHE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-21T12:45:36.000Z","updated_at":"2026-03-17T00:07:44.000Z","dependencies_parsed_at":null,"dependency_job_id":"2fcefd0b-b97e-487f-b2d5-eb87273d7c8b","html_url":"https://github.com/anaslimem/CortexaDB","commit_stats":null,"previous_names":["anaslimem/cortexadb"],"tags_count":15,"template":false,"template_full_name":null,"purl":"pkg:github/anaslimem/CortexaDB","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anaslimem%2FCortexaDB","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anaslimem%2FCortexaDB/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anaslimem%2FCortexaDB/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anaslimem%2FCortexaDB/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/anaslimem","download_url":"https://codeload.github.com/anaslimem/CortexaDB/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anaslimem%2FCortexaDB/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31909235,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-16T18:22:33.417Z","status":"ssl_error","status_checked_at":"2026-04-16T18:21:47.142Z","response_time":69,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agentic-memory","ai-agents","graph-database","python","rust","vector-database"],"created_at":"2026-03-01T16:05:19.040Z","updated_at":"2026-04-17T00:02:06.190Z","avatar_url":"https://github.com/anaslimem.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"https://raw.githubusercontent.com/anaslimem/CortexaDB/main/logo.png\" alt=\"CortexaDB Logo\" width=\"200\" /\u003e\n\u003c/div\u003e\n\n\u003ch1 align=\"center\"\u003eCortexaDB\u003c/h1\u003e\n\u003cp align=\"center\"\u003e\n  \u003csmall\u003eSQLite for AI Agents\u003c/small\u003e\n\u003c/p\u003e\n\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/License-MIT%2FApache--2.0-blue.svg\" alt=\"License\" /\u003e\u003c/a\u003e\n  \u003ca href=\"#current-status\"\u003e\u003cimg src=\"https://img.shields.io/badge/Status-Stable-brightgreen.svg\" alt=\"Status\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/anaslimem/CortexaDB/releases\"\u003e\u003cimg src=\"https://img.shields.io/badge/Version-1.0.1-blue.svg\" alt=\"Version\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://pepy.tech/projects/cortexadb\"\u003e\u003cimg src=\"https://static.pepy.tech/personalized-badge/cortexadb?period=total\u0026units=INTERNATIONAL_SYSTEM\u0026left_color=GRAY\u0026right_color=BLUE\u0026left_text=downloads\" alt=\"Downloads\" /\u003e\u003c/a\u003e\n  \u003ca href=\"https://cortexa-db.vercel.app\"\u003e\u003cimg src=\"https://img.shields.io/badge/Docs-cortexa--db.vercel.app-purple.svg\" alt=\"Documentation\" /\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\n📖 **[Read the full documentation](https://cortexa-db.vercel.app)**\n\n**CortexaDB** is a lightweight, high-performance embedded database built in Rust, specifically designed to serve as the long-term memory for AI agents. It provides a single-file, zero-dependency storage solution that combines the simplicity of SQLite with the semantic power of vector search, graph relationships, and temporal indexing.\n\n---\n\n### The Problem: Why CortexaDB?\n\nCurrent AI agent frameworks often struggle with \"memory\" once the context window fills up. Developers usually have to choose between complex, over-engineered vector databases (that require a running server) or simple JSON files (that are slow and lose searchability at scale). \n\nCortexaDB exists to provide a **middle ground**: a hard-durable, embedded memory engine that runs inside your agent's process. It ensures your agent never forgets, starting instantly with zero overhead, and maintaining millisecond query latencies even as it learns thousands of new facts.\n\n---\n\n### Quickstart\n\n```python\nfrom cortexadb import CortexaDB\nfrom cortexadb.providers.openai import OpenAIEmbedder\n\n# 1. Open database with an embedder \ndb = CortexaDB.open(\"agent.mem\", embedder=OpenAIEmbedder())\n\n# 2. Add facts \nmid1 = db.add(\"The user prefers dark mode.\")\nmid2 = db.add(\"User works at Stripe.\")\ndb.connect(mid1, mid2, \"relates_to\")\n\n# 3. Fluent Query Builder\nhits = db.query(\"What are the user's preferences?\") \\\n    .limit(5) \\\n    .use_graph() \\\n    .execute()\n\nprint(f\"Top Hit: {hits[0].id}\")\n```\n\n---\n\n### Installation\n\nCortexaDB is available on PyPI for Python and can be added via Cargo for Rust.\n\n**Python**\n```bash\npip install cortexadb\npip install cortexadb[docs,pdf]  # Optional: For PDF/Docx support\n```\n\n---\n\n### Core Capabilities\n\n- **100x Faster Ingestion**: New batch insertion system allows processing 5,000+ chunks/second.\n- **Hybrid Retrieval**: Search by semantic similarity (Vector), structural relationship (Graph), and time-based recency in a single query.\n- **Ultra-Fast Indexing**: Uses **HNSW (USearch)** for sub-millisecond approximate nearest neighbor search.\n- **Fluent API**: Chainable QueryBuilder for expressive searching and collection scoping.\n- **Hard Durability**: WAL-backed storage ensures zero data loss.\n- **Privacy First**: Completely local. Your agent's memory stays on your machine.\n\n---\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eTechnical Architecture \u0026 Benchmarks\u003c/b\u003e\u003c/summary\u003e\n\n### Performance Benchmarks (v1.0.1)\n\nMeasured on an M-series Mac — 10,000 embeddings × 384 dimensions.\n\n| Operation | Latency / Time |\n|-----------|---------------|\n| Bulk Ingestion (1,000 chunks) | **0.12s** |\n| Single Memory Add | **1ms** |\n| HNSW Search p50 | **1.03ms** (debug) / ~0.3ms (release) |\n| HNSW Recall | **95%** |\n\nSee the [full benchmark docs](https://cortexa-db.vercel.app/docs/resources/benchmarks) for HNSW vs Exact comparison and how to reproduce.\n\n\u003c/details\u003e\n\n---\n\n## License \u0026 Status\nCortexaDB `v1.0.1` is a **stable release** available under the **MIT** and **Apache-2.0** licenses.  \nWe welcome feedback and contributions!\n\n---\n\u003e *CortexaDB — Because agents shouldn't have to choose between speed and a soul (memory).*\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanaslimem%2Fcortexadb","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fanaslimem%2Fcortexadb","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanaslimem%2Fcortexadb/lists"}