headroomlabs-ai/headroom
Headroom is a context compression layer for AI agents, reducing token usage by 60-95% across tool outputs, logs, RAG chunks, files, and conversation history, while maintaining accuracy.
Awesome AI Agents › End-to-End Optimizers
RUC-NLPIR/Arbor
Arbor is an open-source autonomous research agent from RUC-NLPIR aimed at general-purpose optimization: any task that has a target to improve and a metric to measure it, from model training to harness engineering to data synthesis. The system runs two cooperating LLM agents. A Coordinator acts as research director, maintaining an Idea Tree of hypotheses, driving a six-step search cycle and dispatching experiments. An Executor acts as research engineer, implementing the code changes for a single idea, running the experiment in an isolated git worktree and reporting evidence back. Results, failure modes and distilled insights propagate upward through the tree, so later branches start from what earlier branches learned instead of scrolling out of context. Experiments follow an explicit discipline: executors iterate on a development split, validate on a held-out test split, and only changes that clear a configurable margin are merged, leaving the main branch untouched until the user merges. Arbor can ground ideas in prior work through keyless search backends, including the public alphaXiv API and web search, so a branch can be novelty-checked before compute is spent, either automatically by the Coordinator or manually via an idea-check command. Completed runs leave concrete reusable findings that are recalled at intake on similar future tasks. Model support covers Anthropic, the OpenAI Responses API and OpenAI-compatible backends through LiteLLM, including DeepSeek, Gemini, Qwen, vLLM and Ollama. It can be used as a native command-line runtime or as an Agent Skill Suite inside Codex and Claude Code. Operators get a live dashboard, a read-only web interface, optional human-in-the-loop review and one-line domain plugins for steering runs without touching the core. The repository reports benchmark numbers on BrowseComp, Terminal-Bench 2.0, MLE-Bench Lite and math reasoning data, and is published under Apache 2.0 alongside an arXiv paper.
https://github.com/RUC-NLPIR/Arbor
Also in End-to-End Optimizers
topoteretes/cognee
Cognee is an open-source project that provides scalable and modular memory solutions for AI agents using ECL pipelines, enabling efficient data ingestion, knowledge graph generation, and query capabilities to enhance AI performance and reduce hallucinations.
letta-ai/letta
Letta is an open-source framework for building stateful AI agents with advanced reasoning, transparent long-term memory, and context management, supporting multiple LLM backends and providing a graphical development environment.
langchain-ai/opengpts
OpenGPTs is an open-source platform that replicates and extends OpenAI's GPTs and Assistants API, offering customizable cognitive architectures, extensive tooling, and support for multiple language models and vector databases.
aiwaves-cn/agents
Agents 2.0 is an open-source framework that enables the training and self-evolution of autonomous language agents through symbolic learning inspired by neural network methodologies.
getzep/zep
Zep is an AI memory foundation that uses a temporal Knowledge Graph to enable continuous learning and personalized experiences for AI agents by efficiently managing and retrieving contextual chat and data artifacts.
algorithmicsuperintelligence/optillm
OptiLLM is an optimizing inference proxy that significantly improves the accuracy and performance of large language models on reasoning tasks without requiring any model training, by applying over 20 advanced optimization techniques during inference.
mll-lab-nu/RAGEN
A reinforcement learning framework for training multi-turn reasoning LLM agents on the StarPO algorithm, shipping ten Gym-compatible environments plus diagnostics for echo-trap and reasoning-collapse failure modes.