FollowAgents AI AGENTS DIRECTORY
Home / All Agents / KwaiAgents
Productivity & Collaboration information-seekingweb-browsingweatherapivllmfastchatllama-cppagent-evaluation

KwaiAgents

A lightweight information-seeking agent system runnable with GPT-3.5 or self-hosted KAgent models.

View on GitHub ↗ Quick start ↓
Source repo
KwaiKEG/KwaiAgents
Stars
★ 1.2k
Last updated
2y ago
License
NOASSERTION
Primary language
Python
FA score
44/100 · Major gaps

At a glance

How it runs
CLI
Works with
Portable with changesOpenAI API
Cost
Free software; you pay for model usage
Setup effort
Medium · a few setup steps
You'll need
Python 3.10+MinicondaOpenAI API key for GPT-3.5 usageShell / CLINetwork accessLocal filesystem
Typical use
A team that wants to handle English or Chinese information-seeking queries from a command line using GPT-3.5-turbo.
Not a fit if
  • Teams needing the full KAgentSys: the Lite version has fewer tools and no memory
  • Users without a GPU or unwilling to deploy FastChat/vLLM model services
  • Adopters who need clear license terms before use
Source review
44/100 · Major gaps 1 safety controls not found

What does this agent do, and when should you use it?

KwaiAgents is a collection of agent-related work released by Kuaishou Technology's KwaiKEG, centered on the runnable KAgentSys-Lite system. Its kagentsys CLI accepts a query and can use GPT-3.5-turbo or a deployed local KAgentLM to produce a response. The project also publishes KAgentLMs trained through Meta-agent tuning, the 200k-plus KAgentInstruct dataset, and KAgentBench with more than 3,000 human-edited evaluation examples. KAgentBench evaluates planning, tool use, reflection, concluding, and profiling, then reports dimension scores and an overall score. KAgentSys-Lite is not the paper's full KAgentSys: it has fewer tools, no memory mechanism, somewhat reduced performance, and a codebase evolved from projects including BabyAGI and Auto-GPT.

A user submits a question with kagentsys --query="..." --llm_name="gpt-3.5-turbo" --lang="en", and the system can call GPT-3.5-turbo using OPENAI_API_KEY. For local inference, KAgentSys-Lite can be pointed at an OpenAI-format service started with FastChat and vLLM by using --use_local_llm, --local_llm_host, and --local_llm_port; the Qwen GGUF conversion can also be served on CPU with llama_cpp.server. Weather requests can use WEATHER_API_KEY, while the browse_website tool requires chromedriver on the server. For evaluation, benchmark/infer_qwen.py writes JSONL inference results and benchmark/benchmark_eval.py reads them to report plan, tooluse, reflextion, conclusion, profile, and overall scores.

  1. A team that wants to handle English or Chinese information-seeking queries from a command line using GPT-3.5-turbo.
  2. A user who has deployed Qwen-7B-MAT, Qwen-14B-MAT, or Baichuan2-13B-MAT with vLLM and FastChat and wants to connect it to KAgentSys-Lite.
  3. A developer who needs to serve the Qwen-7B-MAT GGUF model through an OpenAI-compatible endpoint on a CPU-only machine.
  4. A researcher comparing models on planning, tool use, reflection, concluding, and profiling with quantitative KAgentBench results.
  5. An application developer handling weather-related agent queries who can configure WeatherAPI credentials.

How do you install or deploy this agent?

Install Miniconda, then run:

conda create -n kagent python=3.10
conda activate kagent
pip install -r requirements.txt
git clone [email protected]:KwaiKEG/KwaiAgents.git
cd KwaiAgents
python setup.py develop

For GPT-3.5-turbo, set:

export OPENAI_API_KEY=sk-xxxxx

For weather queries, also set:

export WEATHER_API_KEY=xxxxxx

How do you use this agent?

First GPT-3.5-turbo invocation:

kagentsys --query="Who is Andy Lau's wife?" --llm_name="gpt-3.5-turbo" --lang="en"

For a local model, start the FastChat controller, vLLM worker, and OpenAI API server:

python -m fastchat.serve.controller
python -m fastchat.serve.vllm_worker --model-path $model_path --trust-remote-code
python -m fastchat.serve.openai_api_server --host localhost --port 8888

Then run:

kagentsys --query="Who is Andy Lau's wife?" --llm_name="kagentlms_qwen_7b_mat" --use_local_llm --local_llm_host="localhost" --local_llm_port=8888 --lang="en"

What are this agent's strengths and limitations?

Pros
  • It combines a runnable KAgentSys-Lite implementation with KAgentLMs, KAgentInstruct, and KAgentBench, covering operation, models, training data, and evaluation data.
  • It supports both GPT-3.5-turbo through OPENAI_API_KEY and a connection to self-hosted local model services.
  • Its documented local serving options cover vLLM/FastChat on GPU and llama-cpp-python with GGUF on CPU.
  • KAgentBench reports planning, tool use, reflection, concluding, profiling, and overall scores for dimension-level model comparison.
Limitations
  • KAgentSys-Lite explicitly has a more limited tool set and no memory mechanism, so it is not equivalent to the full KAgentSys described in the paper.
  • Local-model use requires deploying FastChat and vLLM or installing llama-cpp-python; the GPU path may also require handling Bfloat16 compatibility.
  • Website browsing requires chromedriver on the server, and repeated search failures may require an http_proxy because duckduckgo_search may be unreachable.
  • The repository license status is NOASSERTION, so adopters need to establish the applicable licensing terms.

How does this agent compare with similar options?

KAgentSys-Lite is positioned as a lighter version of the full KAgentSys: it has a smaller tool set, no memory mechanism, somewhat reduced performance, and a different codebase. The README's human-evaluation table also compares KAgentSys with NoAgent, ReACT, and Auto-GPT; those figures are the project's reported evaluation results.

Key facts side by side with the most closely related agents.

Agent Source review Form / cost Stars Updated Language Full support on
KwaiAgents This agent 44 · Major gaps CLIFree + model costs ★ 1.2k 2y ago Python OpenAI API
AgenticSeek 44 · Major gaps Self-hosted serviceFree + model costs ★ 28k 17d ago Python OpenAI API
Hermes Web UI 68 · Some gaps Web appFree + model costs ★ 19k today Python Codex · Claude Code · OpenAI API · Claude API
Hope Agent 68 · Some gaps Desktop appFree + model costs ★ 1.9k today Rust Codex · OpenAI API · Claude API

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Major gaps
44/ 100 5-point scale 2.2 / 5
Trust 8/29
Reliability 3/14
Adaptability 12/18
Convention 10/18
Effectiveness 7/13
Verifiability 4/8
Why each dimension lost points
Trust8 / 29 · 1.4/5

The README says an OpenAI key and optional weather API key are needed, and identifies browser, search, and local model services, giving limited clues about data flows and permissions. It does not show secret protection, permission reduction, sensitive data handling, pre-action confirmation, or rollback; tool side effects and data destinations are also only lightly described, so these scores are low. The README links a paper, datasets, and models, providing some attribution evidence, but no rules for citing individual outputs are shown.

Reliability3 / 14 · 1.1/5

The README documents model serving, command options, benchmark scores, and limitations of the Lite version, including fewer tools, no memory, and differences from the paper system. These claims are not cross-checked by the supplied code or tests. requirements.txt lists dependencies with only some version constraints, and the README notes that search can fail under network restrictions. No consistency checks or user-facing error handling are shown, so failure messages score zero.

Adaptability12 / 18 · 3.3/5

The README positions the product as a generalized information-seeking agent and shows question answering, weather queries, website browsing, custom tools, and English and Chinese options. It documents environment setup and some operating boundaries. Tool names, iteration limits, and language parameters provide some evidence of configurable triggers, but detailed task-selection rules are not included, so these criteria do not receive full marks.

Convention10 / 18 · 2.8/5

The README organizes model serving, Lite usage, custom tools, and benchmark evaluation, with installation steps, command options, examples, and known limitations. LICENSE.txt identifies CC BY-NC-SA 4.0, supporting a strong license score. Names and release notes are present, but the change history is limited; KwaiKEG/Kuaishou and paper authors are named without a clear maintainer or support path, so maintenance responsibility scores only partially.

Effectiveness7 / 13 · 2.7/5

The README provides usable serving and query commands, a parameter list, and benchmark dimensions and results. It asserts competitive Lite performance and presents benchmark and human evaluation tables, giving some support for its claimed value. Practical applicability of those results and cost-benefit tradeoffs are not explained in enough detail, so effectiveness and cost-benefit scores are reduced.

Verifiability4 / 8 · 2.5/5

Usage steps, dependency notes, links to the paper, datasets, and models, and benchmark tables make some claims traceable. The license and requirements files offer additional kinds of evidence, but the supplied materials contain no source code or tests to corroborate README behavior and performance claims. Evaluation figures are shown without enough explanation separating measured facts from broader inferences, so these scores remain limited.

Risks and how to mitigate them
  • Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
  • The supplied packet is mainly a README, license, and dependency list; it contains no implementation code or tests, so benchmark figures and runtime behavior cannot be independently checked from this evidence.
  • The guide asks users to configure API keys and may use external search, browser, or model services, but does not describe secret storage, data transfer details, action confirmation, or reversal procedures.
  • The license is CC BY-NC-SA 4.0, whose noncommercial term limits commercial use.
Evidence confidence: Low Reviewed Nov 08, 2026 Reviewed revision 3504ab8a00a3
Review evidence README.mdLICENSE.txtrequirements.txt
See the full review method →
Maintain this project? Add the FARS badge to your README

The badge shows the current review score and verdict and links back to this page. It refreshes about once an hour after a re-review.

FARS

[![FARS review](https://followagents.com/badge/kwaiagents.svg)](https://followagents.com/en/agents/kwaiagents)
<a href="https://followagents.com/en/agents/kwaiagents"><img src="https://followagents.com/badge/kwaiagents.svg" alt="FARS review"></a>

FAQ

What credentials are needed for GPT-3.5-turbo?
Set OPENAI_API_KEY. Weather-related queries additionally require WEATHER_API_KEY.
Does KAgentSys-Lite include memory?
No. The project explicitly states that the Lite system lacks memory mechanisms.
Can it run without a GPU?
Yes. The README documents a CPU-serving path using llama-cpp-python and the Qwen-7B-MAT GGUF model.
What should I check if browsing or search fails?
browse_website requires chromedriver. For repeated search failures, the README notes that duckduckgo_search may be inaccessible and suggests setting http_proxy.
Was this page helpful?
View on GitHub ↗ Install ↓