agent-framework agents

153 tagged agent-framework, measured the same way as everything else here.

Browse within: agentic-ai 240ai-orchestration 160agent-teams 129ai-automation 129agent-orchestration 86claude-ai 54agentic-workflow 45ai-memory 40knowledge-management 40markdown 40Autonomous Agents 37ai-development 36fastapi 34agentic-automation 29

agentlas-ai/Agentlas-OS

Agent Claude Code

Use this agent when the user asks for /meta-agent, a single agent builder, multi-agent team builder, or packaging existing agents into Agentlas architecture.

not rated 1.6k +13 today A 38 tokens original Apache-2.0

stack-auditor

02

RyanAlberts/best-of-Agent-Harnesses

Agent Claude Code

Audits a codebase's AI agent stack against the live best-of-Agent-Harnesses dataset — finds which harnesses the repo uses, flags dead or graveyarded ones, and names live replacements. Use when the user asks "is my agent stack current", "audit my agent dependencies", or inherits an agent project of unknown vintage.

not rated 1.2k +109 5d ago A 73 tokens CC-BY-SA-4.0

architecture

03

Azure/GPT-RAG

Agent Claude Code ✓ vendor

Analyzes GPT-RAG boundaries, contracts, security, deployment topology, and trade-offs. Use for structural or hard-to-reverse changes; do not use for local implementation work with settled requirements.

not rated 1.2k 17d ago A 41 tokens original MIT

CronusL-1141/AI-company

Agent Claude Code

A technical lead agent that guides a development team's technical direction. It plans work, assigns tasks, reviews implementation, and coordinates decisions across the team.

not rated 372 +1 changed 15d ago A 50 tokens original MIT

spec-writer

06

Insajin/autopus-adk

Agent Claude Code

A specification-writing agent that examines a codebase and turns a feature request into four project documents: requirements, a plan, acceptance checks, and research.

not rated 111 changed 1mo ago A 45 tokens original MIT

npc-mind

07

LudicDynamics/WorldLines

Agent Claude Code

A private-mind agent for one named character at a time. It reacts only from that character’s personal point of view and must be given the character’s ID.

not rated 94 +3 10d ago A 101 tokens

qos-cost-optimizer

08

qualixar/qualixar-os

Agent Claude Code

Budget-aware task routing using Qualixar OS cost engine. Analyzes task complexity, selects the cheapest model that meets quality requirements, and tracks spend against budget. Uses POMDP routing for optimal cost/quality tradeoff.

not rated 47 +3 14d ago A 51 tokens

haiku-xhigh

09

dryvist/ai-assistant-instructions

Agent Claude Code

Fallback executor, used only when codex-quota exits 1 (Codex runs first otherwise), for scoping, bulk reads, triage, mechanical shipping and implementation chunks delegated by a lead session. Runs at xhigh effort, never below high; reports evidence to the file the prompt names. Brief it completely: it knows only its…

not rated 9 changed 3d ago A 75 tokens original Apache-2.0

infrastructure-ops

10

RD-DCS/venutian-antfarm

Agent Claude Code

Infrastructure operations agent. Owns deployment infrastructure, container orchestration, and application-level observability.

not rated 5 6mo ago A 24 tokens

wick

11

agoradynamics/wick

Agent Claude Code

Wick — persistent thinking partner with philosophical frameworks, operational gates, calibration discipline, and epistemic humility. Invoke for decision analysis, strategic questions, framework application, or any question where depth > fluency matters. Keeps memory in memory/ folder.

not rated 3 13d ago A 51 tokens

review-agent

12

fentas/cuite

Agent Claude Code

Code review and quality analysis specialist.

not rated 2 8mo ago A 9 tokens

engineering-lead

13

alessio-locatelli/ceo-agent-workflow

Agent Claude Code

Hands‑on technical leader who translates product vision into scalable architecture, mentors engineers, and drives delivery excellence. Proactively steps in during sprint kickoff, when architectural decisions surface, or whenever blockers threaten timelines—to ensure the team stays aligned, code quality remains high…

not rated 2 3mo ago A 62 tokens original Apache-2.0

puller

14

jaroslavsoucek-art/Giovanni

Agent Claude Code

AI Chief of Staff methodology for Claude Code. Memory · daily digest · predictive layer with anti-self-fulfilling invisible shadow hypotheses · governance · subagents · slash commands · adversarial-default review.

not rated 2 1mo ago A 2 tokens original MIT

research-agent

15

Razaib-khan/ForgeWeave

Agent Claude Code

Investigates one subtopic by crawling URLs and extracting usage-focused code examples.

not rated 1 3mo ago A 14 tokens original MIT

coder

16

SabilMurti/Seiza

Agent Claude Code

Writes and modifies code files based on the plan.

not rated 1 2mo ago A 12 tokens

Orchestrator

17

saajunaid/caddis-plugin

Agent Claude Code

Pipeline brain - reads pipeline state, validates artefact contracts, and routes between agents. Does not write code or create designs. Manages the supervised-autonomous workflow.

not rated 0 changed 20d ago A 0 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: