fast-agentevalstate/fast-agent
An ultra-lightweight, high-concurrency autonomous agent runtime optimized for sub-millisecond execution latency.…
No ratings yet
Rate this skill
Stars3.9k
Forks453
Watchers3.9k
Open Issues43
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/evalstate/fast-agent.git
OverviewOverview
Key Features
An ultra-lightweight, high-concurrency autonomous agent runtime optimized for sub-millisecond execution latency. Key capabilities include: 1. bare-metal async event loops (strips framework overhead to drive agent tool execution through high-throughput asynchronous streams); 2. streaming argument parsing and pre-warming (validates tool arguments on the fly during token generation to pre-warm network sockets); 3. resilient concurrency pool scaling (orchestrates thousands of concurrent agent sessions with exponential backoff and circuit breaking).
Use Cases
Agent Workflow Orchestration, Autonomous Agent Assembly, High-Concurrency Performance Optimization.
Target Roles
AI / Algorithm Engineer, Full-stack / Indie Developer.
TopicsTopics
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 | 262 |
|---|---|
| Data source | GitHub |
| Repository | evalstate/fast-agent |
| Category | AI Agent Architecture & RAG / Agent Orchestration & Workflow |
| Primary language | Python |
| License | Apache License 2.0 |
| Default branch | main |
| GitHub repository ID | 918778709 |
| Node ID | R_kgDONsNzVQ |
| Rank | #317 (position within the source ranking) |
| Site-wide popularity rank | #317 (computed live from Stars, across all 5833 entries) |
GrowthStar / Fork growth
One snapshot per day, tracking how Stars and Forks changed
- Now3,947
- Previous point · 11-02 3,947
- vs previous point ±0
- 6 data points 37 days
- Now453
- Previous point · 11-02 453
- vs previous point ±0
- 6 data points 37 days
TimelineTimeline
Repository created2025-01-18 20:39:512025-01-18
Data last updated2026-11-05 10:05:1512 days ago
Last commit2026-10-23 16:46:2324 days ago
CommitLatest commit
Version [5.6] committed by evalstate. Category: Maintenance & Optimization. Commit message: Benchmarks: publish TB2.1 GPT-5.6 Luna high (6h, OpenAI flex).