Agents IA
honcho
Honcho — Plastic Labs' memory library for stateful agents that learn about their users over time.
★ 7,5 k étoilesAGPL-3.0
Voir le guide →// agents · vectorize-io/hindsight
hindsight
hindsight est un projet de agents IA open source, créé par vectorize-io (vectorize-io/hindsight sur GitHub). Il compte 47 008 étoiles sur GitHub et 5 967 forks, il est publié sous la licence MIT et a été mis à jour pour la dernière fois sur GitHub le 7 octobre 2026.
Agent memory that learns — so your agents get smarter over time.
★ 47,0 k étoiles⑂ 6,0 k forksMITmis à jour oct. 2026
▦ visuel — le README de ce projet ne contient aucune capture intégrable,
voici donc un emplacement réservé. Le guide ci-dessous est complet malgré tout.
voici donc un emplacement réservé. Le guide ci-dessous est complet malgré tout.
// détails du projet
Détails du projet
- Étoiles GitHub
- 47 008
- Forks
- 5 967
- Licence
- MIT
- Dernière mise à jour sur GitHub
- 7 octobre 2026
- Catégorie
- Agents IA
- Type de fiche
- Guide d'installation complet
- Site officiel
- Official site
// fonctionnement
Comment ça marche
- Clarify your goal
Decide what you want the project to do before installing anything.
- Clone the repo
Grab the source and skim the README for setup requirements.
- Install and configure
Install dependencies and add any API keys or settings it needs.
- Run your first task
Launch it and follow the example workflow from the docs.
// fonctionnalités
Pourquoi on l'adore
Learning memory
Recall that improves instead of just accumulating.
Persistent recall
Agents remember across sessions.
Python SDK
Drop it into Python agent stacks.
Agent-framework friendly
Designed to slot into existing agent builds.
Built by Vectorize
From the team behind vectorize-io tooling.
MIT licensed
Free for commercial use.
Advertisement
// lancez-le
Lancez-le vous-même
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/vectorize-io/hindsight.git cd hindsight - 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 hindsight # check README for the exact command
// cas d'usage
Ce que vous pouvez créer
- Give support agents memory of past tickets.
- Let coding agents recall earlier decisions.
- Build assistants that learn user preferences.
- Add long-term context to multi-session workflows.
Advertisement
// faq
Questions fréquentes
Who maintains hindsight?
It is an open-source project at vectorize-io/hindsight with 5967 forks. Check the contributors tab and recent commits to judge how active maintenance is.
Is hindsight free to use?
Yes — it's MIT licensed: free to use, modify, and ship commercially. Just keep the license notice in copies.
How does the memory learn?
It persists interaction history and refines recall over time — the docs at hindsight.vectorize.io cover the architecture.
Does it replace a vector database?
It's a memory layer, not just storage: retrieval plus learning. You may still use a vector DB underneath.
How do I get started?
Clone the repo and follow the README quickstart — the docs at https://hindsight.vectorize.io/ walk through setup.
// continuez l'exploration
Outils similaires
Agents IA
gini-agent
Gini: a personal agent runtime that remembers, learns skills, and reaches you with the right control in time.
★ 1,9 k étoilesMIT
Voir le guide →Agents IA
graphiti
Real-time knowledge graphs that give agents a memory with structure.
★ 31,5 k étoilesApache-2.0
Voir le guide →Agents IA
letta
Stateful AI agents with memory that learns and improves.
★ 25,1 k étoilesApache-2.0
Voir le guide →Agents IA
Memori
Agent-native memory infrastructure - structured, persistent memory for production agents
★ 17,1 k étoilesNOASSERTION
Voir le guide →Agents IA
qwen-audio-agent
Real-time voice runtime that keeps AI agents talking, working, and present.
★ 2,8 k étoilesApache-2.0
Voir le guide →// alternatives
Alternatives en Agents IA
Les autres projets de la catégorie Agents IA avec le plus d'étoiles du catalogue LibreAI — la sélection réaliste d'alternatives si hindsight ne vous convient pas.
- openclaw★ 391,6 k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294,9 k
An agentic skills framework & software development methodology that works.
- ECC★ 275,2 k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252,0 k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245,5 k
DeepSeek's plugin-based agent harness where everything is a plugin.
// plus en agents
Plus en Agents IA
Projets de la catégorie Agents IA proches dans le catalogue, les plus proches en étoiles de hindsight — continuez à explorer de part et d'autre.
- nanobot★ 48,8 k
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat…
- siyuan★ 46,6 k
An open-source, privacy-first, self-hosted knowledge workspace where humans and AI agents work together 开源、隐私优先、自托管的知识工作空间，让人与智能体在此协作
- LocalAI★ 49,4 k
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
- milvus★ 46,3 k
The cloud-native vector database for planet-scale similarity search.
- multica★ 51,9 k
Make humans and AI agents work as one team — open-source and self-hostable.
- codebase-memory-mcp★ 46,1 k
High-performance code intelligence MCP server: your codebase as a persistent knowledge graph
Obtenir hindsight
Gratuit et ouvert : récupérez le code source, mettez une étoile au dépôt et commencez à créer.