Agents
trpc-agent-go
Go framework for production agent systems: graphs, tools, memory, A2A, MCP.
★ 1.8k starsApache-2.0
View guide →// agents · vectorize-io/agent-memory-benchmark
agent-memory-benchmark
agent-memory-benchmark is an open-source ai agents project by vectorize-io (vectorize-io/agent-memory-benchmark on GitHub). It has 144 GitHub stars and 47 forks, is released under the NOASSERTION license, and was last updated on GitHub on 7 October 2026.
A benchmark for comparing AI agent memory systems head-to-head.
★ 144 stars⑂ 47 forksNOASSERTIONupdated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- vectorize-io/agent-memory-benchmark
- GitHub stars
- 144
- Forks
- 47
- License
- NOASSERTION
- Last updated on GitHub
- 7 October 2026
- Category
- AI Agents
- Listing
- Full install guide
// how it works
How it works
- Define the job
Know what you want the agent to accomplish before touching any code.
- Get the code
Clone the repo and read the README's requirements section.
- Wire up dependencies
Install what's needed and add API keys or configuration.
- Take it for a spin
Run the quickstart example, then iterate from there.
// features
Why people love it
Standardized tasks
Same tests for every system.
Head-to-head comparisons
Apples-to-apples memory evals.
Memory-focused
Recall quality, not generic chat.
Open methodology
Inspect how scores are computed.
Vectorize-built
From the Hindsight team.
Active development
Updated as the field moves.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/vectorize-io/agent-memory-benchmark.git cd agent-memory-benchmark - Step 2 — Create a venv and install
Isolate dependencies, then install requirements.
python -m venv .venv && source .venv/bin/activate pip install -r requirements.txt - Step 3 — Run it
Launch using the entry point shown in the README.
python -m agent_memory_benchmark # check README for the exact command
// use cases
What you can build
- Compare memory systems fairly.
- Validate memory product claims.
- Research memory architectures.
- Choose a memory layer with data.
Advertisement
// faq
Questions, answered
Who maintains agent-memory-benchmark?
It is an open-source project at vectorize-io/agent-memory-benchmark with 47 forks. Check the contributors tab and recent commits to judge how active maintenance is.
Is agent-memory-benchmark free to use?
GitHub lists no license for this repo, so legally it's all rights reserved — check the README or ask the maintainer before building on it.
What does it measure?
How well agent memory systems recall and use information — standardized tasks for head-to-head comparison.
Who's it for?
Researchers and vendors who want memory performance as numbers, not claims.
How do I get started?
Clone the repo and follow the README quickstart — the README is the best starting point.
// keep exploring
Similar tools
AI Agents
Agent_Memory_Techniques
30 runnable notebooks teaching everything about agent memory.
★ 1.1k starsApache-2.0
View guide →AI Agents
webarena-verified
WebArena-Verified: the audited, deterministically scored release of the WebArena web-agent benchmark.
★ 62 starsApache-2.0
View guide →AI Agents
OpenViking
A self-evolving context database unifying agent memory, RAG, and skills.
★ 39.4k starsAGPL-3.0
View guide →AI Agents
osaurus
Osaurus — own your AI: a native macOS agent harness with any model, memory and fully offline execution.
★ 8.0k starsMIT
View guide →AI Agents
memanto
A memory agent for your agent fleet: it curates, reconciles, and expires shared memories across tools.
★ 2.3k starsMIT
View guide →// alternatives
Alternatives in AI Agents
The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if agent-memory-benchmark is not the right fit.
- openclaw★ 391.6k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294.9k
An agentic skills framework & software development methodology that works.
- ECC★ 275.2k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252.0k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245.5k
DeepSeek's plugin-based agent harness where everything is a plugin.
// more in agents
More in AI Agents
Nearby AI Agents projects in the catalogue, closest in stars to agent-memory-benchmark — keep exploring the shelf either side of it.
- octomind★ 151
An MCP-native AI coding agent and runtime in a single binary.
- OpenYabby★ 130
A voice-driven multi-agent assistant that orchestrates in realtime.
- evals★ 230
A complete evaluation toolkit for AI agents.
- babyagi_archive★ 110
A frozen snapshot of the original BabyAGI autonomous-agent experiment.
- WorkArena★ 275
WorkArena: ServiceNow's benchmark for how well web agents handle everyday knowledge-work tasks.
- ActPlane★ 104
eBPF-powered information-flow enforcement for safer AI agents.
Get agent-memory-benchmark
Free and open — grab the source, star the repo, and start creating.