1. vectorize-io/hindsight
Hindsight: Agent Memory That Learns
GitHub repository with 15,667 stars and 889 forks.
Trending score: 4.22; stars gained: +129; forks gained: +10.
Language: Python
Topics: agentic-ai, memory, agents, ai-memory
Discover trending repositories tagged memory, ranked by recent growth and activity.
Hindsight: Agent Memory That Learns
GitHub repository with 15,667 stars and 889 forks.
Trending score: 4.22; stars gained: +129; forks gained: +10.
Language: Python
Topics: agentic-ai, memory, agents, ai-memory
OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density
GitHub repository with 3,036 stars and 217 forks.
Trending score: 3.92; stars gained: +201; forks gained: +18.
Language: Python
Topics: agent, ai, ai-agents, deep-learning, foundation-models, llm
What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?
GitHub repository with 22,915 stars and 1,748 forks.
Trending score: 3.09; stars gained: +36; forks gained: +3.
Language: TypeScript
Topics: agents, ai, context-window, framework, llms, memory
Memory engine and app that is extremely fast, scalable. The Memory API for the AI era.
GitHub repository with 25,557 stars and 2,238 forks.
Trending score: 2.81; stars gained: +921; forks gained: +55.
Language: TypeScript
Topics: agent-memory, ai-memory, cloudflare-kv, cloudflare-pages, cloudflare-workers, drizzle-orm
ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, and any AI agent to query data accurately through MCP with skills, memory and a semantic layer
GitHub repository with 878 stars and 45 forks.
Trending score: 2.76; stars gained: +24; forks gained: +1.
Language: TypeScript
Topics: agent, agent-skills, agents, ai-agent, ai-agents, analytics
TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastructure ceiling.
GitHub repository with 40,130 stars and 6,196 forks.
Trending score: 2.23; stars gained: +4; forks gained: +4.
Language: Go
Topics: agent, agent-context, agent-memory, agentic, ai, cloud-native
OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system paradigm, enabling hierarchical context delivery and self-evolving.
GitHub repository with 25,151 stars and 1,935 forks.
Trending score: 2.20; stars gained: +93; forks gained: +11.
Language: Python
Topics: agent, agentic-rag, ai-agents, clawbot, context-database, context-engineering
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
GitHub repository with 9,563 stars and 868 forks.
Trending score: 1.94; stars gained: +59; forks gained: +4.
Language: TypeScript
Topics: agent, llm, memory, long-term-memory, memory-management, rag
A curated solutions to building a self-evolving second brain that helps AI agents understand your personal and team context.
GitHub repository with 250 stars and 15 forks.
Trending score: 1.82; stars gained: +68; forks gained: +3.
Topics: anthropic, awesome, awesome-lists, chatgpt, claude, context
local multi-agent harness
GitHub repository with 206 stars and 23 forks.
Trending score: 1.60; stars gained: +42; forks gained: +6.
Language: TypeScript
Topics: agents, claude-code, free, harness, harness-engineering, memory
Your favorite self-hostable alternative to Google Timeline (Google Location History)
GitHub repository with 9,193 stars and 304 forks.
Trending score: 1.59; stars gained: +27; forks gained: +1.
Language: Ruby
Topics: google-maps, maps, self-hosted, homelab, owntracks, gpslogger
Use your NVIDIA GPU's VRAM as swap space on Linux. Built for laptops with soldered memory and no upgrade path. If you have an RTX card sitting there with 8GB of VRAM and you're getting swapped to SSD, this puts that VRAM to work
GitHub repository with 391 stars and 10 forks.
Trending score: 1.53; stars gained: +39; forks gained: +0.
Language: Shell
Topics: cuda, gpu, laptop, linux, memory, nbd
Real AI agent for your vault. Coworker, Copilot & thinking partner, that maintains your memory & knowledge, adapts to your workflows, uses plugins, skills & tools with full safety controls. BYOK & MCP.
GitHub repository with 119 stars and 17 forks.
Trending score: 1.45; stars gained: +31; forks gained: +1.
Language: TypeScript
Topics: ai, automation, knowledge-management, llm-wiki, memory, obsidian-plugin
AI-native HTAP database with Git-for-Data and built-in vector search, serving as the data and memory backbone for intelligent agents and applications.
GitHub repository with 1,845 stars and 298 forks.
Trending score: 1.44; stars gained: +2; forks gained: +0.
Language: Go
Topics: agents, ai-native, cloud-native, database, distributed-database, distributed-systems
Local-first Memory OS for personal AI assistants with L0-L3 memory, Wiki++ knowledge, skill routing, and TokenLess context compression.
GitHub repository with 122 stars and 15 forks.
Trending score: 1.34; stars gained: +24; forks gained: +4.
Language: TypeScript
Topics: ai-agent, ai-assistant, knowledge-graph, local-first, memory, openclaw
Self-maintaining, Obsidian-compatible knowledge base for pi — turn raw sources into an interlinked wiki that compounds over time. Follows Karpathy's LLM Wiki pattern.
GitHub repository with 95 stars and 7 forks.
Trending score: 1.29; stars gained: +20; forks gained: +0.
Language: TypeScript
Topics: karpathy, knowledge-base, llm-wiki, markdown, memory, obsidian
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems.
GitHub repository with 15,181 stars and 2,543 forks.
Trending score: 1.16; stars gained: +11; forks gained: +6.
Language: Python
Topics: agent, ai, long-short-term-memory, memory, python, rag
Hermes scoped memory provider with SQLite truth, LanceDB semantic recall, and nightly workflow digest.
GitHub repository with 63 stars and 3 forks.
Trending score: 1.05; stars gained: +11; forks gained: +0.
Language: Python
Topics: agent, ai-agent, ai-memory, hermes, hermes-agent, hermes-plugin
Memory that AI Agents Love!
GitHub repository with 355 stars and 190 forks.
Trending score: 1.01; stars gained: +10; forks gained: +4.
Language: Python
Topics: ai-agents, memory, moorcheh, memanto, agent-memory, crewai
Openloomi is your open-source proactive AI Mates that remembers all work details.
GitHub repository with 97 stars and 10 forks.
Trending score: 0.98; stars gained: +6; forks gained: +2.
Language: TypeScript
Topics: agent, ai, claw, harness-engineering, llm, llm-model
MTuner is a C/C++ memory profiler and memory leak finder for Windows, PlayStation 3/4/5, Nintendo Switch, Android and other platforms
GitHub repository with 2,781 stars and 160 forks.
Trending score: 0.86; stars gained: +4; forks gained: +0.
Language: C++
Topics: profiling, memory-profiler, memory-leak-finder, memory, optimization, tool
The native macOS & iOS app for browsing AI agent memory files — Claude Code, OpenClaw, Codex, Cursor, Gemini
GitHub repository with 30 stars and 3 forks.
Trending score: 0.78; stars gained: +2; forks gained: +0.
Language: Swift
Topics: agentic-tools, ai-agents, ai-tools, anthropic, claude, claude-code
Hardened allocator designed for modern systems. It has integration into Android's Bionic libc and can be used externally with musl and glibc as a dynamic library for use on other Linux-based platforms. It will gain more portability/integration over time.
GitHub repository with 1,879 stars and 145 forks.
Trending score: 0.78; stars gained: +5; forks gained: +0.
Language: C
Topics: malloc, security, memory-allocation, malloc-library, memory-allocator, memory
CheetahClaws: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Using AI Systems
GitHub repository with 717 stars and 259 forks.
Trending score: 0.76; stars gained: +5; forks gained: +2.
Language: Python
Topics: agentic-ai, claude, claude-code, memory, openclaw, python