ai-agents — independent software & tools
-
Spanlens
Open source LLM observability and monitoring. Drop-in proxy for OpenAI, Anthropic, and Gemini with request logging, cost tracking, and agent tracing. Self-host with one Docker command. MIT.
-
Incident-Investigator
Stateful MCP server for incident investigation: dynamic evidence planning, competing hypotheses, confidence scoring, timelines, blast radius, and postmortems. Works with Cursor, Claude Code, Codex, and any MCP client.
-
waggle
A social network substrate for autonomous AI agents — keypair identity, E2EE messaging, escrowed information trades, a verifiable knowledge graph, staked-prediction forecasts, multi-agent projects, and a reputation economy. BYO-brain; the platform is the rail, not the mind.
-
claude-code-life
An AI-native template for running your life as one Git repo with Claude Code — designed so the primary reader is the AI, not humans.
-
Do-SOUL-Alaya
The local-first memory plane for CLI coding agents. Codex and Claude Code attach via MCP; SQLite-backed, evidence-gated, no GUI. Cross-session memory that the agent proposes and a governance gate decides.
-
thingctx
Drive any agent against any W3C WoT Thing from its description. No per-integration server.
-
tinkering
Small AI-assisted operator tools, released as I build them. Starting with a LinkedIn engagement console that drafts grounded comments instead of generic ones.
-
research-repo-doctor
Artifact Evaluation readiness checker for research code: static scan, safe fixes, verify ladder, appendix, and agent-ready gates. Local-first, no API key.
-
trustabl-action
GitHub Action that runs trustabl — static reliability/safety analyzer for AI agent SDKs (Claude, OpenAI, Google ADK, MCP). Gates CI on risk + severity.
-
pxml
Prompt with XML to project [ALPHA]
-
auxly-memory-cli
A local-first, file-based memory CLI for AI tools. Own your context in plain Markdown — auditable, versionable, and provider-agnostic.
-
nothumansearch
Search engine for AI agents — ranks sites by agentic readiness (llms.txt, OpenAPI, MCP, ai-plugin). MCP server, REST API, full-text search. 8,000+ indexed sites.
-
obsidian-memory-kit
An operational prompt that lets an agent set up persistent, cross-device memory for itself using Obsidian MCP and a private GitHub vault on Windows.
-
compass
Product development framework for AI-assisted teams. Bets, roles, decisions — all in markdown
-
Yggdrasil
Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Markdown). Works with Claude Code, Codex & any MCP host.
-
vonzio
The runtime for production agents — bring your own model. Open-source, self-hostable, isolated Docker workspaces per session.
-
power-framework
P.O.W.E.R. - Hybrid Knowledge Management Framework (P.A.R.A. + OKF Overlay + LLM-Wiki + Execution Rules)
-
quilt
Tracks which agent wrote which lines when multiple AI agents share one Git checkout.
-
Xenesis
AI agent workbench desktop for terminals, MCP tools, Capability Registry, and live UI rendering
-
tela
Open-source, self-hostable markdown team wiki with a built-in MCP server — so AI agents read, write, and search your docs as first-class teammates. Live multiplayer, semantic + full-text search. Go + PostgreSQL + React/Milkdown.
-
add-mcp
Add MCP servers to your favorite coding agents with a single command.
-
agent-relay-codex
Codex integration for Agent Relay — auto-registers sessions as agents and enables inter-agent messaging
-
agent-relay-plugin
Claude Code plugin for Agent Relay — auto-registers sessions as agents and enables inter-agent messaging
-
agent-relay-server
Lightweight HTTP message relay for inter-agent communication across machines
-
agentdb
Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1
-
agentic-flow
The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches
-
@aifinpay/agent
Unified agent-economy SDK for autonomous AI agents — chain-opaque AiFinPayAgent surface (call/openSession/balance/verify) over Polygon and Solana execution environments.
-
aiwg
Deployment tool and support utility for AI context. Copies agents, skills, commands, rules, and behaviors into the paths each AI platform reads (Claude Code, Codex, Copilot, Cursor, Warp, OpenClaw, and 6 more) so one source of truth works across 10 platfo
-
@axiomatic-labs/claudeflow
Claudeflow — AI-powered development toolkit for Claude Code and Codex. Skills, agents, hooks, and quality gates that ship production apps.
-
@calebux/agent-kit
Infrastructure for autonomous agent economies — identity, reputation, payments, governance, discovery, coordination, and audit on Celo and Stellar. Also works fully off-chain with persistent memory, agentic loops, and tool-use.
-
@claude-flow/cli
Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code
-
@claude-flow/mcp
Standalone MCP (Model Context Protocol) server - stdio/http/websocket transports, connection pooling, tool registry
-
@claude-flow/neural
Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear
-
e2b
E2B SDK that give agents cloud environments
-
eve
Filesystem-first framework for durable backend AI agents that run anywhere.
-
@fatihkan/badi
Workflow management CLI for Claude Code, Cursor, and Gemini CLI — 30 AI agents (incl. a virtual eng team, ads strategist, market/SEO/data analysts), 86 commands, OWASP security scans. Built for Anthropic Claude Opus and Sonnet.
-
@hayasaka7/haya-pet
Generic AI CLI pet runtime foundation.
-
kodelyth-ecc
Production-grade AI coding toolkit — 70 agents (incl. devil-mode adversarial crew), 194 skills, 97 commands, parallel multi-agent commands, semantic intent routing, self-learning memory, and a built-in MCP server (16 tools / 6 prompts / 377 resources) tha
-
loki-mode
Loki Mode by Autonomi. Autonomous spec-to-product system: takes a PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief to a deployed app via the RARV-C closure loop with 8 quality gates. Provider-agnostic (Claude Code, OpenAI Codex, Cline, Aider).
-
loki-mode-sdk
TypeScript SDK for Loki Mode - autonomous multi-agent development platform
-
loomlog
Local, cross-agent dev journal for Claude Code, Codex & Gemini CLI — passively weaves your AI coding sessions into an Obsidian-compatible vault.
-
mage-memory
mage — a portable, self-maintaining knowledge base for software systems: durable git-backed notes navigable as an Obsidian graph, usable by any AI coding agent. CLI: init, index, skills, ingest, redact, observe, connect, dream, link, verify, unlink, list,
-
@mcp-b/transports
Browser transport implementations for Model Context Protocol (MCP) - postMessage, Chrome extension messaging, and iframe communication for AI agents and LLMs
-
openvisio
Cut your AI coding agent's token usage. MCP server + CLI that turns any codebase into a deterministic code graph and serves Claude Code, Cursor, Codex & Windsurf a ranked, token-budgeted query surface — agents query structure (symbols, imports, call edges
-
paqad-ai
Spec-driven development framework — AI agents that think before they type
-
prjct-cli
Project memory and workflow context for AI coding agents.
-
@promptbook/utils
Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action
-
sdlc-ai-workflow
Complete SDLC Workflow Plugin for Claude Code: 26 agents, 43 skills, 14 commands, 6 phases. Covers planning → design → development → testing → deployment → operations, with industry-standard SDLC best practices embedded in every agent.
-
skills
The open agent skills ecosystem
-
sneakoscope
Sneakoscope Codex: fast proof-first Codex trust layer with image-based Voxel TriWiki.
-
specrails-core
AI agent workflow system for Claude Code — installs 12 specialized agents, orchestration commands, and persona-driven product discovery into any repository
-
takt
Workflow control for AI coding agents
-
the-frame-ai
FRAME — Framework for AI-Assisted Solo Development
-
workspace-architect
A comprehensive library of specialized AI agents and personas for GitHub Copilot, ranging from architectural planning and specific tech stacks to advanced cognitive reasoning models.
-
tron
A deterministic supervisor that builds software from specs — one agent you talk to; it runs the fleet.
-
claude-skills-marketplace
🛠️ Transform Claude into a System Architect, generating detailed project documentation for AI-assisted software development with clear boundaries and traceable requirements.
-
claude-memory
Enable persistent memory for Claude that works across crashes and restarts in both Claude Code and Claude Cowork environments.
-
oh-no-my-claudecode
Memory-grounded autonomous coding loops for Claude Code and Codex, with verifier gates, replay, evals, and tamper-evident receipts.
-
forgemax
Collapse multiple servers and tools into two sandboxed MCP tools for efficient, typed JavaScript execution with secure resource access and concurrency.
-
memoria
🗂️ Organize messy social media exports into well-structured media libraries with accurate dates for easy access and management.