SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-18 UTC

No new commits yet today

Open the update feed

nexentModelEngine-Group/nexent

A practical framework for building multi-agent and Agentic RAG applications, turning "let the LLM plan, call tools,…

No ratings yet Rate this skill
Stars6k
Forks754
Watchers6k
Open Issues284

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/ModelEngine-Group/nexent.git

OverviewOverview

Key Features

A practical framework for building multi-agent and Agentic RAG applications, turning "let the LLM plan, call tools, retrieve knowledge and collaborate autonomously" from scattered scripts into a reusable engineering structure. Key capabilities include: 1. Multi-agent collaboration orchestration: define multiple agents with distinct responsibilities and organize their collaboration flow, so complex tasks are split across roles and processed in parallel or in sequence, reducing the burden on a single agent handling all logic at once; 2. Agentic RAG retrieval augmentation: combine retrieval-augmented generation with agent decision-making, letting the agent decide when to retrieve, what to retrieve, and how to continue reasoning from retrieved results, improving traceability of answers in knowledge Q&A tasks; 3. MCP tool integration: mount external tools and data sources for agents to call via MCP (Model Context Protocol), so agents can actually execute queries and read/write actions instead of only generating text; 4. Agentic workflow orchestration: chain agents, tools and retrieval steps into a workflow, breaking a full task into an observable and adjustable node chain that makes it easier to locate failing steps and iterate; 5. Harness engineering support: provide a harness mechanism for agent execution, constraints and evaluation, lowering the cost of moving from a demo to a usable system.

Use Cases

scenarios that require the LLM to autonomously complete multi-step tasks, such as building multi-role collaborative assistants, constructing Agentic RAG Q&A over enterprise knowledge bases, exposing internal APIs or data sources to agents through MCP, and debugging and validating agent workflow chains.

Target Roles

AI / Algorithm Engineer, Backend Developer, Full-stack / Indie Developer, Data Analyst / Data Engineer.

TopicsTopics

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID202
Data sourceGitHub
RepositoryModelEngine-Group/nexent
CategoryAI & Agent Skills / Multi-Agent & Agent Frameworks
Primary languagePython
LicenseMIT License
Default branchdevelop
GitHub repository ID974157595
Node IDR_kgDOOhB3Gw
Rank#195 (position within the source ranking)
Site-wide popularity rank#237 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02k4k6k8k2026-09-242026-10-242026-09-24 · 5,8892026-10-19 · 5,9602026-10-23 · 6,0132026-10-24 · 6,025
  • Now6,025
  • Previous day · 10-23 6,013
  • vs previous day +12
  • 4 data points 30 days
02004006008002026-09-242026-10-242026-09-24 · 7332026-10-19 · 7432026-10-23 · 7502026-10-24 · 754
  • Now754
  • Previous day · 10-23 750
  • vs previous day +4
  • 4 data points 30 days

TimelineTimeline

Repository created2025-04-28 10:44:332025-04-28
Data last updated2026-10-26 11:54:1023 days ago
Last commit2026-10-24 07:01:3325 days ago

CommitLatest commit

committed by cj2026-bit. Category: Bug Fixes & Stability Improvements. Commit message: 🐛 Fix(e2e): resolve the Daily checkout without the cwd and run the AI….

848cf42 cj2026-bit 2026-10-19

Next stepsNext steps