awesome-repositories.com
Blog
MCP
awesome-repositories.com

Descoperă cele mai bune repository-uri open source cu căutare AI.

ExploreazăCăutări recomandateAlternative open-sourceSoftware self-hostedBlogHartă site
ProiectServer MCPDespreCum realizăm clasamentulPresă
LegalConfidențialitateTermeni
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
posgnu avatar

posgnu/rci-agent

0
View on GitHub↗
240 stele·33 fork-uri·HTML·MIT·10 vizualizăriposgnu.github.io/rci-web↗

Rci Agent

Welcome to the codebase for our paper, "Language Models can Solve Computer Tasks". In this codebase, you will find the implementation of our RCI agent, which uses a pre-trained language model to execute computer tasks in MiniWoB++ benchmark guided by natural language. The agent employs a simple…

Features

  • Agent Memory Systems - Recursive criticism and improvement for solving computer tasks.
  • Task Automation Agents - Solving computer-based tasks using language model reasoning.

Istoric stele

Graficul istoricului de stele pentru posgnu/rci-agentGraficul istoricului de stele pentru posgnu/rci-agent

Căutare AI

Explorează mai multe repository-uri excelente

Descrie ce ai nevoie în limbaj simplu — AI-ul sortează mii de proiecte open source selectate în funcție de relevanță.

Start searching with AI

Alternative open-source pentru Rci Agent

Proiecte open-source similare, clasificate după numărul de funcționalități comune cu Rci Agent.
  • mnemox-ai/tradememory-protocolAvatar mnemox-ai

    mnemox-ai/tradememory-protocol

    1,259Vezi pe GitHub↗

    The Tradememory Protocol is a persistent, multi-layered memory and audit framework designed for artificial intelligence trading agents. It provides a structured architecture for agents to maintain episodic, semantic, and procedural knowledge across trading sessions, ensuring that decision-making is informed by long-term recall and historical context. The framework distinguishes itself through a combination of cryptographic integrity and cognitive modeling. It employs a tamper-evident logging system that uses hashed sequences to verify the history of trading decisions, alongside an outcome-wei

    Pythonai-agentsclaudecrypto
    Vezi pe GitHub↗1,259
  • aiwaves-cn/agentsAvatar aiwaves-cn

    aiwaves-cn/agents

    5,932Vezi pe GitHub↗

    This is an LLM agent framework and symbolic learning system designed for building self-evolving autonomous agents. It functions as a computational graph orchestrator that organizes agent interactions and tool sequences as a trainable graph of nodes. The framework focuses on data-centric agent optimization, allowing agent pipelines and prompts to be upgraded through data-driven training rather than manual engineering. It utilizes a symbolic learning process that applies language-based loss and textual reflections to refine the operational logic and symbolic components of an agent. The system

    Pythonautonomous-agentslanguage-modelllm
    Vezi pe GitHub↗5,932
  • baai-agents/cradleAvatar BAAI-Agents

    BAAI-Agents/Cradle

    2,538Vezi pe GitHub↗

    The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

    Pythonaiai-agentai-agents-framework
    Vezi pe GitHub↗2,538
  • airi-institute/arigraphAvatar AIRI-Institute

    AIRI-Institute/AriGraph

    170Vezi pe GitHub↗

    AriGraph functions as the external memory architecture for large language models (LLMs), featuring a knowledge graph that is built from the ground up. This memory, configured as a semantic knowledge graph with added episodic vertices and edges, greatly improves the performance of…

    Inform 7
    Vezi pe GitHub↗170
Vezi toate cele 27 alternative pentru Rci Agent→

Întrebări frecvente

Ce face posgnu/rci-agent?

Welcome to the codebase for our paper, "Language Models can Solve Computer Tasks". In this codebase, you will find the implementation of our RCI agent, which uses a pre-trained language model to execute computer tasks in MiniWoB++ benchmark guided by natural language. The agent employs a simple…

Care sunt principalele funcționalități ale posgnu/rci-agent?

Principalele funcționalități ale posgnu/rci-agent sunt: Agent Memory Systems, Task Automation Agents.

Care sunt câteva alternative open-source pentru posgnu/rci-agent?

Alternativele open-source pentru posgnu/rci-agent includ: mnemox-ai/tradememory-protocol — The Tradememory Protocol is a persistent, multi-layered memory and audit framework designed for artificial… aiwaves-cn/agents — This is an LLM agent framework and symbolic learning system designed for building self-evolving autonomous agents. It… baai-agents/cradle — The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer… canner/wrenai — WrenAI is a platform designed to enable natural language interaction with relational and analytical databases. By… cpacker/memgpt — MemGPT is a memory management framework and external memory layer for large language models. It functions as a… airi-institute/arigraph — AriGraph functions as the external memory architecture for large language models (LLMs), featuring a knowledge graph…