Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to build an AI agent
-
dolt
Agents & frameworksDolt – Git for Data
git clone https://github.com/dolthub/dolt.git -
agent-memory
Agents & frameworksLong-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.
git clone https://github.com/tigerless-labs/agent-memory.git -
agent-memory-benchmark
Agents & frameworksAgent Memory Benchmark
git clone https://github.com/vectorize-io/agent-memory-benchmark.git -
ai-agent-book
Agents & frameworks《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码
git clone https://github.com/bojieli/ai-agent-book.git -
agent-memory-atlas
Agents & frameworksComparison of memory systems for agents
git clone https://github.com/neoneye/agent-memory-atlas.git -
honcho
Agents & frameworksMemory library for building stateful agents
git clone https://github.com/plastic-labs/honcho.git -
claude-smart
Agents & frameworksTurns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.
git clone https://github.com/ReflexioAI/claude-smart.git -
kungfu
Agents & frameworksYour agents don’t hand off the work. Kungfu keeps the same Work moving across Codex, Claude, OpenCode, and your own execution surface.
git clone https://github.com/kungfu-systems/kungfu.git -
Orbital
Agents & frameworksContext is yours. Agents are replaceable.
git clone https://github.com/zqiren/Orbital.git -
GenericAgent
Agents & frameworksSelf-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
git clone https://github.com/lsdefine/GenericAgent.git -
awesome-harness-engineering
Agents & frameworksAwesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
git clone https://github.com/ai-boost/awesome-harness-engineering.git -
memanto
Agents & frameworksMemory that AI Agents Love!
git clone https://github.com/moorcheh-ai/memanto.git -
PlugMem
Agents & frameworksICML 2026 | PALM@NeurIPS2026 Oral | Plug-and-play long-term memory for LLM agents
git clone https://github.com/TIMAN-group/PlugMem.git -
agentic-context-engine
Agents & frameworks🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
git clone https://github.com/kayba-ai/agentic-context-engine.git -
Intent
Agents & frameworksSemantic Git for the vibe coding era
git clone https://github.com/dozybot001/Intent.git -
magic-context
Agents & frameworksUnbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.
git clone https://github.com/cortexkit/magic-context.git -
caura-long-run-fleet
Agents & frameworksLong-running fleet orchestration and memory infrastructure for AI agents. Enables persistent context, shared memory, task execution, and governed coordination across multi-agent systems.
git clone https://github.com/caura-ai/caura-long-run-fleet.git -
AIPass
Agents & frameworksPersistent Agent Workspace — AI agents that remember, collaborate, and never start from zero.
git clone https://github.com/AIOSAI/AIPass.git -
agenticow
Agents & frameworksGit for Agent Memory: Copy-On-Write vector branching for embedded multi-agent memory (83x faster, 3000x smaller snapshots)
git clone https://github.com/ruvnet/agenticow.git -
yantrikdb-hermes-plugin
Agents & frameworksYantrikDB memory provider for NousResearch/hermes-agent — self-maintaining memory with benchmarked recall, self-tuning ranking, contradiction tracking, proactive hygiene, and explainable recall.
git clone https://github.com/yantrikos/yantrikdb-hermes-plugin.git -
GateMem
Agents & frameworksGateMem: a benchmark and evaluation toolkit for memory governance in multi-principal shared-memory LLM agents.
git clone https://github.com/rzhub/GateMem.git -
mycelium
Agents & frameworksMycelium is a shared workspace for AI coding agents and the people who run them.
git clone https://github.com/mycelium-io/mycelium.git -
ForgeDock
Agents & frameworksForgeDock — autonomous AI dev pipeline for Claude Code. GitHub as agent memory: issue in, PR out.
git clone https://github.com/RapierCraftStudios/ForgeDock.git -
inno-agent
Agents & frameworksAn open-source personal learning agent with three-layer memory (learner profile / wiki knowledge base / cross-conversation recall), a proactive scheduler, personal IM channels, and a workspace-scoped Practice Lab — built on the Pi SDK.
git clone https://github.com/hhyqhh/inno-agent.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.