Data / Repositories / Agent memory
Agent memory repositories on GitHub: 24 ranked by stars
24 public repositories tagged Agent memory are on GitHub, with 141,728 stars between them; 23 had a push in the last 30 days. Most are written in Python (11), TypeScript (6), Rust (3). The most starred: volcengine/OpenViking (39,910), topoteretes/cognee (32,287), supermemoryai/supermemory (31,225).
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 |
|---|---|---|---|---|---|---|---|
| volcengine/OpenViking | Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. | Python | 39,910 | 3,170 | AGPL-3.0 | Oct 14 | Oct 14 |
| topoteretes/cognee | Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free | Python | 32,287 | 3,363 | Apache-2.0 | Oct 14 | Oct 14 |
| supermemoryai/supermemory | Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era. | TypeScript | 31,225 | 2,748 | MIT | Oct 14 | Oct 14 |
| semantica-agi/semantica | Graph-Native Infrastructure for Context and Accountable AI Systems | Python | 14,039 | 1,630 | MIT | Oct 14 | Oct 14 |
| deeplethe/utopia | World's first open-source enterprise world model. | Rust | 8,349 | 1,155 | Apache-2.0 | Oct 14 | Oct 14 |
| plastic-labs/honcho | Memory library for building stateful agents | Python | 7,610 | 938 | AGPL-3.0 | Oct 14 | Oct 14 |
| ai-boost/awesome-harness-engineering | Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration. | Python | 4,828 | 649 | Oct 14 | Oct 14 | |
| doobidoo/mcp-memory-service | Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation. | Python | 2,014 | 347 | Apache-2.0 | Oct 14 | Oct 14 |
| angelnicolasc/graymatter | 30 sec to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality. | Go | 483 | 41 | MIT | Oct 9 | Oct 14 |
| Graphicle-AI/graphicle | Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client. | Rust | 335 | 27 | Apache-2.0 | Oct 21 | Oct 21 |
| Avinash-jetwani/jevmem | jevmem saves the decisions, rules and failed approaches from your Claude Code chats to JEVMEM.md in your repo, and brings the relevant ones back next session. | TypeScript | 123 | 10 | MIT | Oct 15 | Oct 15 |
| AskTheWay/dsh-auto-memory | Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt. File-only, no external services. | TypeScript | 106 | 7 | MIT | Oct 13 | Oct 15 |
| kunwar-shah/claudex | MCP server with persistent memory + FTS5 search for Claude Code conversation history. Index your ~/.claude/projects/, expose 10 MCP tools, browse via web UI. MIT-licensed. | JavaScript | 96 | 11 | MIT | Jun 20 | Oct 14 |
| major7apps/pensyve | Universal memory runtime for AI agents | Rust | 96 | 16 | Oct 8 | Oct 14 | |
| Kerneta/daidocs | Open plain-text file format for AI memory. Your assistant's long-term memory as .dai files on your disk: readable by Claude, GPT, Gemini, Cursor, local models and grep (all LLM… | Python | 53 | 4 | Apache-2.0 | Oct 7 | Oct 14 |
| Abhigyan-Shekhar/Waggle-mcp | MCP server for external memory layer for AI agents + more . Download from pypi , and get started | Python | 44 | 139 | Apache-2.0 | Oct 9 | Oct 14 |
| tashfeenahmed/scallopbot | Self-hosted personal AI assistant with MCP-native, bio-inspired memory. OpenClaw-compatible skills. LoCoMo F1 0.48 vs 0.38. | TypeScript | 44 | 7 | MIT | Oct 4 | Oct 14 |
| RxAi-Aus/amp | Shared memory for AI agents, no database, no server, just a GitHub repo. Memories that worked get stronger; memories that failed fade. | JavaScript | 31 | 4 | Oct 7 | Oct 14 | |
| star-ga/mind-mem | Persistent AI memory for Claude Code, OpenClaw, and any MCP-compatible agent. BM25F + vector hybrid, governance-aware, local-first, zero-infrastructure. | Python | 18 | 4 | Apache-2.0 | Oct 14 | Oct 14 |
| renezander030/agentic-task-system | CLI + MCP for agent context: a task layer over TickTick, Notion, GitHub, Obsidian & more (RRF retrieval, provenance, reviewed writes, undo) plus a knowledge-graph layer — ats kg… | JavaScript | 16 | 3 | MIT | Oct 14 | Oct 14 |
| frankxai/Starlight-Intelligence-System | One shared brain for your whole AI fleet: attested memory, orchestration, governance and evals across Claude Code, Codex, Cursor, Gemini, Antigravity. | TypeScript | 11 | 3 | MIT | Oct 14 | Oct 14 |
| shimo4228/contemplative-agent | A long-running experiment: an AI agent posts on its own with a local LLM (Ollama, one 16 GB Mac) and proposes changes to its harness (the constitution, identity and skills in its… | Python | 7 | 2 | MIT | Oct 14 | Oct 14 |
| akadal/assistant | A personal memory core for AI assistants — plain markdown, plain git, no service to run. Two layers, one write gate, sleep consolidation. | Python | 2 | 0 | MIT | Oct 11 | Oct 14 |
| SAIHM-Admin/saihm-mcp-server-pro | Portable memory for AI agents — enterprise-ready production thin-client. Seals agent memory client-side (ML-DSA-65 / AES-256-GCM / ML-KEM-768) and stores opaque ciphertext on the… | TypeScript | 1 | 0 | Apache-2.0 | Oct 13 | Oct 14 |
By language
- Python 11
- TypeScript 6
- Rust 3
- JavaScript 3
Related topics
- AI agents 18
- MCP 15
- LLM 11
- Claude Code 11
- Context engineering 10
- Memory 10
- MCP server 10
- AI memory 8
- Knowledge graph 8
- AI 6
- Model Context Protocol 6
- TypeScript 5
Read from GitHub by SpecStream between October 14, 2026 and October 21, 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.