llm-council
○ queued
A council of several LLMs that answer hard questions together.
filters
symphony
○ queued
Turns project tasks into isolated autonomous runs so teams manage work instead of babysitting coding agents.
hermes-agent
◐ testing
Self-improving agent from Nous Research with a built-in learning loop; desktop build, MIT.
paperclip
○ queued
Open app for managing working agents.
nasiko
○ queued
Developer control plane: a dashboard for your own AI agents.
agency-agents
○ queued
Ready-made set of digital-agency agents (frontend, community, review), each with its own role and process.
openclaude
○ queued
Open terminal agent that runs anywhere and uses any LLM.
repo-task-proof-loop
◐ testing
Spec-driven skill that spawns subagents for repository tasks.
OmniRoute
● in use
Free MIT gateway: one endpoint, 290+ providers (90+ free), 500+ models; quota fallback, context compression, MCP/A2A.
gpt4free
○ queued
Collection of free/bypass providers for language-model access. Legal status and stability of such proxies are unverified.
context7
● in use
Platform that feeds up-to-date library documentation to LLMs and AI editors.
claude-mem
● in use
Cross-session memory: records agent actions, compresses them with AI, and injects relevant context into later sessions.
GitNexus
○ queued
Client-side (in-browser, no server) knowledge-graph builder for a repository with a built-in Graph-RAG agent.
Understand-Anything
◐ testing
Turns a codebase into an interactive knowledge graph you can search and question.
codebase-memory-mcp
○ queued
MCP server that indexes a codebase into a persistent knowledge graph: 158 languages, sub-millisecond queries.
beads
◐ testing
A memory upgrade for your coding agent.
hindsight
○ queued
Agent memory that learns from experience.
chroma-mcp
○ queued
MCP server giving an agent access to the Chroma vector database.
headroom
● in use
Compresses tool output, logs, files and RAG chunks before they reach the LLM (claimed ~20% for coding agents, 60–95% on JSON). Library, proxy, MCP server.
maxkb
○ queued
Enterprise-grade open-source platform for building agents on top of a knowledge base.
searxng
◐ testing
Free metasearch engine aggregating results from many engines without tracking users.
strix
◐ testing
Open-source AI pentest tool: finds application vulnerabilities and helps fix them.
skill-scanner
● in use
Security scanner for agent skills: check what is inside before installing.
prowler
○ queued
Open cloud-security platform: automates security and compliance checks across cloud environments.
ECC
◐ testing
Agent-harness optimization system: skills, instincts, memory, security, research-first approach. Formerly everything-claude-code.
awesome-claude-code-toolkit
◐ testing
Large collection: 135 agents, 35 skills, 42 commands, 176+ plugins, hooks, rules, MCP configs.
SuperClaude_Framework
○ queued
Configuration framework: specialized commands, cognitive personas, development methodologies.
Claude-Code-Everything-You-Need-to-Know
○ queued
Practical guide: setup, prompt engineering, slash commands, skills, hooks, subagents, MCP.
adhd
● in use
Tree-of-thought with pruning on the Agent SDK: parallel divergence across cognitive frames, then scoring and deepening the survivors.
i-have-adhd
○ queued
Skill that stops the agent burying the answer: ADHD-friendly output format.
no-ai-slop
◐ testing
Strips 20+ common AI-filler patterns out of text.
open-design
◐ testing
Local desktop analogue of Claude Design: a coding agent as a design engine (prototypes, landings, dashboards, slides, video) with HTML/PDF/PPTX/MP4 export.
diagram-design
○ queued
Skill for editorial diagrams (29 types per the description, 27 per the README), outputting HTML + SVG instead of Mermaid. Picks up brand style from a site and redraws draw.io files.
remotion-video-director
○ queued
Interactive Claude Code skill for making Remotion videos through an expert discussion.
instagram-cli
○ queued
Agent (and MCP) for working with Instagram from the CLI.
open-seo
○ queued
Open alternative to Semrush and Ahrefs.
OpenSandbox
○ queued
Secure, fast and extensible sandbox runtime for AI agents.
autoresearch
○ queued
AI agents autonomously running research on training nanochat on a single GPU.
MiroFish
○ queued
Simple general-purpose swarm-intelligence engine for forecasting.
personaplex
◐ testing
Real-time full-duplex speech-to-speech model with persona control via a role prompt and voice audio conditioning (Moshi architecture).