agent-framework agents

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

Browse within: ai-orchestration 179ai-automation 155agent-teams 148agent-orchestration 125claude-ai 55agentic-workflow 53Code Generation 50Autonomous Agents 47ai-memory 43knowledge-management 43markdown 43context-engineering 40ai-development 36fastapi 35

memory

121

adeelahmad/agentrc

Agent

Cross-sprint learning, curated at each retrospective. Entries are advisory and never relax an invariant. First agentic-agile session in this repo (Sprint 1); seeded from the 2026-07-02/03 docs+examples+spec audit that produced this work order.

not rated 4 1mo ago A 0 tokens original Apache-2.0

definition-format

122

dsswift/ion

Agent

Markdown frontmatter format for defining reusable agents.

not rated 4 3d ago A 9 tokens original MIT

discovery

123

dsswift/ion

Agent

How the engine finds and loads agent definition files.

not rated 4 3d ago A 10 tokens original MIT

multi-model

124

dsswift/ion

Agent

Per-agent model selection for cost optimization and task specialization.

not rated 4 3d ago A 11 tokens original MIT

wick

125

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 8d ago A 51 tokens

metis-code-explorer

126

gsaranti/pantheon

Agent Claude Code

Investigate one question against the existing codebase. Returns an inline report; writes nothing.

not rated 3 11d ago A 24 tokens original MIT

gsaranti/pantheon

Agent Claude Code

Investigate one technical question against the open web; return findings inline.

not rated 3 11d ago A 21 tokens original MIT

metis-task-reviewer

128

gsaranti/pantheon

Agent Claude Code

Review one implementation diff against the description, plan, and scope report it was meant to satisfy. Return a verdict with per-criterion evidence.

not rated 3 11d ago A 34 tokens original MIT

lantisprime/claude-sdlc

Agent Claude Code

Part of sdlc-plugin

Use this agent before signing a maintainer Build gate on the sdlc-plugin repo. Conditionally reviews dependency manifest changes (package.json, requirements.txt, go.mod, Gemfile, pom.xml, Cargo.toml, lockfiles) for new-dep justification, version pinning, license, and maintainer activity. Self-exits with a…

not rated 3 4mo ago A 121 tokens original MIT

lantisprime/claude-sdlc

Agent Claude Code

Part of sdlc-plugin

Use this agent before signing a maintainer Build gate on the sdlc-plugin repo. Reviews the current diff for security concerns from the security-review skill checklist (input validation, authN/authZ, secrets, injection surfaces, dependency hygiene, sensitive data, output encoding, error handling, cryptography, infra…

not rated 3 4mo ago A 105 tokens original MIT

scope-ingest

131

lantisprime/claude-sdlc

Agent

Part of sdlc-plugin

Bounded subagent that turns raw source material (markdown files, plain-text files, pasted text) into a normalized, provenance-traced scope draft at .claude/sdlc/scope-drafts/. Invoked by the plan skill when scope.md does not yet exist and the human points at a source. Write scope is restricted to scope-drafts/ only …

not rated 3 4mo ago A 85 tokens original MIT

build-agent

132

fentas/cuite

Agent

File implementation and modification specialist.

not rated 2 6mo ago A 8 tokens

review-agent

133

fentas/cuite

Agent

Code review and quality analysis specialist.

not rated 2 6mo ago A 9 tokens

scout-agent

134

fentas/cuite

Agent

Read-only codebase exploration and research agent.

not rated 2 6mo ago A 12 tokens

wf-or

135

mgallet92i/waterfall

Agent

Part of waterfall

Deterministic driver of the wf-orchestrate.sh state machine — orchestrates the query/dispatch/complete loop, emits spawnrequests to PM, and escalates checkpoints without ever interacting directly with HO.

not rated 2 1mo ago A 44 tokens original MIT

wf-pm

136

mgallet92i/waterfall

Agent

Part of waterfall

PM additional instructions for the VALIDATION and CLOTURE phases.

not rated 2 1mo ago A 17 tokens original MIT

wf-tl

137

mgallet92i/waterfall

Agent

Part of waterfall

Author of design.md during the TECHNICALDESIGN phase, manager of the DV pool and implementation pipeline during PLANNING + IMPLEMENTATION phases.

not rated 2 1mo ago A 34 tokens original MIT

br3eze-code/br3eze-code

Agent

Upgrade agents/ask-engine.js into the central, observable orchestration boundary for AgentOS while preserving existing behavior and keeping CLI/PWA/channel adapters thin.

not rated 2 4d ago A 0 tokens original Apache-2.0

deck-cleanup

139

agentdecksdk/agentdeck

Agent Claude Code

Runs ONE narrow entropy scan over agentdeck (narrative comments, dead code, duplicate helpers, or pattern drift) and opens one small evidence-backed PR.

not rated 2 4d ago A 36 tokens original MIT

deck-dev

140

agentdecksdk/agentdeck

Agent Claude Code

Implements a GitHub issue (feature or bug fix) for agentdeck end-to-end in an isolated worktree and opens one PR to dev.

not rated 2 4d ago A 33 tokens original MIT

docs-writer

141

agentdecksdk/agentdeck

Agent Claude Code

Writes or rewrites ONE docs-site page for agentdeck, outline first. Emphasizes clarity, conciseness, and verified code examples.

not rated 2 4d ago A 33 tokens original MIT

QUILL

142

frontier-infra/adl

Agent Claude Code

Version: 1.0.0 Layer: 2 of 4 (Role overlay) Inherits: CLAUDE.md.

not rated 2 1mo ago A 0 tokens original MIT

SCOUT

143

frontier-infra/adl

Agent Claude Code

Version: 1.0.0 Layer: 2 of 4 (Role overlay) Inherits: CLAUDE.md.

not rated 2 1mo ago A 0 tokens original MIT

WARDEN

144

frontier-infra/adl

Agent Claude Code

Version: 1.0.0 Layer: 2 of 4 (Role overlay) Inherits: CLAUDE.md.

not rated 2 1mo 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: