Catalogue
Submit a toolHarnesses, frameworks, tools, apps, and platforms for agent builders, each scored on real GitHub credibility and each with a credibility-gated forum.
171 tools · showing 49–72
ToolLEANN
Memory
StarTrail-org
Stop storing embeddings, and still keep your recall. LEANN is a low‑storage vector index that recomputes embeddings on t
vector-dbraglocal-firstlow-storage
ToolMesh LLM
Deployment
Mesh-LLM
Distributed LLM inference that pools GPUs across machines and serves one OpenAI-compatible API, splitting large models across nodes
distributed-inferenceopenai-compatiblegpulocal-first
ToolOpenCodex
Coding
lidge-jun
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, an
proxygatewaycodexcli
HarnessOsaurus
InferenceMemory
osaurus-ai
Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity
productivitylocal-firstmacosdesktopmlx
PlatformSuperlinked Inference Engine (SIE)
InferenceDeploymentData Wrangling
superlinked
Self-hosted Kubernetes inference cluster serving LLMs, embeddings, rerankers, OCR and vision models with cluster-wide batching.
inference-serverkubernetesrerankingocr
ToolClaude Obsidian
MemoryData Wrangling
AgriciDaniel
Claude Code skills that file dropped sources into a self-organizing Obsidian vault of linked Markdown notes
productivityobsidianknowledge-graphknowledge-baselocal-first
ToolCodeGraph
CodingMemory
colbymchenry
Pre-indexed code knowledge graph for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer
knowledge-graphcode-intelligencesearchtoken-optimization
ToolLLM Space
CodingQA
deer-flow
A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first
desktopobservabilitydebuggingprompt
ToolLocal Deep Research
Research
LearningCircuit
Self-hosted assistant that runs iterative, cited research across search engines with local or cloud LLMs
productivitylocal-firstragcitationsollama
ToolMemorix
MemoryCoding
AVIDS2
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravit
cross-agent-memorycoding-agentlocal-firstcli
ToolMemPalace
Memory
mempalace
Local-first AI memory that stores conversations verbatim and retrieves them by semantic search over a structured, scoped index
vector-dbsemantic-searchlocal-firstcli
ToolODS
DeploymentInterfaceInference
Osmantic
Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.
local-firstollamacomfyuin8n
ToolOpen Science
ResearchInterface
ai4s-research
Open Science Desktop — local-first, model-agnostic AI research workbench for macOS, Windows & Linux. Open-source Claude Science desktop alte
scientific-researchdesktoptaurireproducible-research
ToolRapid-MLX
Inference
raullenchai
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache,
apple-siliconmlxlocal-firstollama-alternative
ToolRaven
CodingMemoryMonitoring
EverMind-AI
The memory-first, self-improving agent harness built on EverOS, with MiroThinker-powered deep research and reasoning.
self-improvementlocal-firstobservabilityskill
ToolTencentDB Agent Memory
Memory
TencentCloud
Local long-term memory for AI agents using a layered semantic pipeline and symbolic compression of tool logs
local-firstlong-term-memoryvector-dbrag
ToolAgentInspect
MonitoringQA
rajudandigam
Local execution trees for TypeScript AI agents. agent-inspect helps you understand what happened inside an AI agent run — locally. It turns
execution-tracetrajectory-testingci-cdlocal-first
ToolAsm
Coding
luongnv89
Use Claude Code, Codex, Cursor, and Windsurf together and skills scatter fast. asm gives that mess one CLI/TUI across 19
local-firstcliclaudecodex
ToolAtomic Agent
InterfaceMemoryInference
AtomicBot-ai
Local First Ai Agent. Optimized for Local Ai models. Long context window. Proper tools callings. Runs privately on your device.
local-firstllama-cppcomputer-usebrowser-automation
ToolAvibe
CodingInterfaceConnectors
avibe-bot
The local-first Agent OS — your AI partner lives on your own machine. Drive the official Claude Code, Codex & OpenCode from your browser or
local-firstremote-controlmulti-agentworkbench
ToolCocoindex Code
Coding
cocoindex-io
CocoIndex Code helps coding agents look up the right code before they start opening files. It builds a local AST-aware s
code-intelligenceasttree-sittersearch
PlatformExo
InferenceDeployment
exo-explore
Open-source distributed inference runtime that pools everyday devices into one local cluster to serve frontier models behind an OpenAI-compatible API.
distributed-inferencedevice-clusteropenai-compatiblelocal-first
ToolHermes Browser Extension
Interface
abundantbeing
Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime.
pluginlocal-firstsidepanelmulti-agent-threads
ToolLoopX
CodingMonitoring
huangruiteng
Lightweight loop engineering state kernel for long-running AI agent teams. Agent-loop agnostic across Codex, Claude Code, and other coding a
control-planelong-horizonmulti-agentgovernance