Agents tagged "litellm"

15 results
litellm ×
Dev & Engineering

LLMix

A production LLM call layer for AI agents and tools: keep your existing SDKs, hot-swap models via MDA presets, and add cache, retries, circuit breakers, and key rotation.

★ 132 FS 67 Some gaps 18d ago Apache-2.0
Dev & Engineering

CaveAgent

Turn LLMs into stateful runtime operators: inject, manipulate, and retrieve real Python objects instead of shuffling text.

★ 202 FS 62 Some gaps 8d ago MIT
Dev & Engineering

Arbor Research Optimizer

A hypothesis-tree agent for running, validating, and retaining metric-driven improvements.

★ 1.1k FS 55 Major gaps 16d ago Apache-2.0
Dev & Engineering

mini-swe-agent

A minimal Bash-driven software-engineering agent for GitHub issues and command-line tasks.

★ 7.9k FS 54 Major gaps 2d ago MIT
Dev & Engineering

Parlant Conversation Control

A Python control harness for governed, traceable customer-facing AI conversations.

★ 18k FS 53 Major gaps 2mo ago Apache-2.0
Dev & Engineering

CocoIndex Code

Embedded AST-based semantic and structural search for code agents.

★ 2.7k FS 52 Major gaps 1d ago Apache-2.0
Dev & Engineering

ACE Context Learning Engine

Turns agent feedback and execution traces into reusable strategies.

★ 2.6k FS 51 Major gaps 2d ago Apache-2.0
Dev & Engineering

MassGen

Coordinate multiple models in parallel to refine, critique, and vote on a final answer.

★ 1.1k FS 51 Major gaps 3mo ago NOASSERTION
Automation & Ops

Hive Agent Harness

A production runtime for multi-agent business workflows with graph execution, recovery, observability, and human oversight.

★ 11k FS 46 Major gaps 10d ago Apache-2.0
Productivity & Collaboration

Commonly

A self-hosted workspace where humans and cross-runtime agents coordinate persistent work.

★ 1.4k FS 44 Major gaps today Apache-2.0
Dev & Engineering

KodeAgent

A lightweight Python engine for planning, tool-using, and code-executing AI agents.

★ 40 FS 43 Major gaps 1mo ago Apache-2.0
Dev & Engineering

OpenAlpha Evolve

Evolve Python algorithms through LLM-generated code, testing, selection, and iterative refinement.

★ 1.1k FS 41 Major gaps 1y ago MIT
Data & Analysis

Meta ARE

Evaluate AI agents on evolving, real-world tasks that demand multi-step reasoning and adaptation.

★ 557 FS 37 Major gaps 28d ago MIT
Dev & Engineering

WorldSeed

A YAML-defined world engine for running, observing, and steering emergent multi-agent scenarios.

★ 822 FS 37 Major gaps 4mo ago MIT
Dev & Engineering

TapeAgents

Build, debug, serve, and improve LLM agents through replayable Tape session logs.

★ 318 FS 25 Major gaps 11mo ago Apache-2.0