AgentClawNegai-ai/AgentClaw
Orchestrate LLM agent workflows declaratively while keeping tool calls safe under a controlled loop and risk policy.…
No ratings yet
Rate this skill
Stars330
Forks35
Watchers330
Open Issues2
InstallOne-line install
UnconfirmedWhether 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/Negai-ai/AgentClaw.git
OverviewOverview
Key Features
Orchestrate LLM agent workflows declaratively while keeping tool calls safe under a controlled loop and risk policy. Key capabilities include: 1. Declarative workflows: define agent flows declaratively and compose multi-step tasks without hand-writing scheduling code; 2. Agentic LLM nodes: embed LLM-driven nodes in the flow so the model performs reasoning and decisions at designated steps; 3. Controlled agentic loop: set loop boundaries and termination conditions to prevent endless calls and runaway execution; 4. Safer tool execution: constrain the tools an agent may call to reduce risks from mistaken invocations; 5. Explicit risk policy: declare which operations are allowed or blocked via explicit policy so behavior boundaries are auditable; 6. Custom extensibility: extend nodes and tools as needed to fit your own business logic; 7. Server and configuration: start the service via server.py, manage runtime parameters and model configuration with .env and models.json, and validate quickly with the bundled hello_world sample agent.
Use Cases
Development stages that connect LLM agents to real business processes and control tool-call risk, including multi-step task orchestration, tool-call safety governance, local agent service setup, and sample validation.
Target Roles
AI / Algorithm Engineer, Backend Developer, Full-stack / Indie Developer.
RatingUser ratings
Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.
RepositoryRepository
| Skill ID | 2199 |
|---|---|
| Data source | GitHub |
| Repository | Negai-ai/AgentClaw |
| Category | AI & Agent Development / Agent Workflow Orchestration |
| Primary language | Python |
| License | Apache License 2.0 |
| Default branch | main |
| GitHub repository ID | 1230894777 |
| Node ID | R_kgDOSV32uQ |
| Rank | #1753 (position within the source ranking) |
| Site-wide popularity rank | #1968 (computed live from Stars, across all 5833 entries) |
GrowthStar / Fork growth
One snapshot per day, tracking how Stars and Forks changed
- Now330
- Previous point · 09-14 343
- vs previous point -13
- 2 data points 29 days
- Now35
- Previous point · 09-14 34
- vs previous point +1
- 2 data points 29 days
TimelineTimeline
Repository created2026-05-06 12:28:416 months ago
Data last updated2026-10-26 12:22:0322 days ago
Last commit2026-06-08 09:10:255 months ago
CommitLatest commit
Version [1.1.7] committed by Negai-ai. Update Category: Bug Fixes & Stability Improvements. Commit details: chore: release 1.1.7 public agent fixes. This update resolves known runtime errors and enhances system reliability.