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.
310 tools · showing 241–264
ToolSpacedock
CodingQA
spacedock-dev
Pi ships four tools ... read, write, edit, bash ... and calls it done. No MCP, no sub-agents, no permission dialogs, no
human-in-the-loopmulti-agentorchestrationgovernance
ToolAgentic Context Engine
Memory
kayba-ai
Agentic Context Engine gives agents a Skillbook that changes after tasks, failures, and feedback. Execution traces go th
agent-learningself-improvementtoken-optimizationskillbook
ToolAgentKey
Research
chainbase-labs
Connect your AI agent to the world — Web search, Social media, Crypto & On-chain data. One plugin, zero extra config.
financesocial-mediaon-chain-datascrapecli
ToolAos Ce
DeploymentSecurity
unicity-aos
AOS Community Edition: the open agent operating system.
clisandboxdaemon
ToolEmbedAnything
Data WranglingMemoryInference
StarlightSearch
Rust-based inference, ingestion and indexing library for embeddings and retrieval, with Python bindings.
local-firstcloudragsdk
ToolExxperts
Memory
EXXETA
Local-first agentic runtime with persistent AI rooms whose memory writes pass through a user-controlled approval gate
local-firsthuman-in-the-loopapproval-gatedcli
ToolKoala
Voice
Picovoice
Audio noise-reduction filter using Picovoice's Koala on-device technology.
noise-reductionon-devicepicovoicecross-platform
ToolMLC LLM
Inference
mlc-ai
Machine-learning compiler and engine for deploying LLMs across AMD, NVIDIA, Apple, and Intel GPUs, browsers, iOS, and Android
cross-platformwebgpuon-devicequantization
ToolTianshu-Tui
CodingInterfaceMemory
huiliyi37
天枢 (Tianshu) 是一个基于harness工程的终端编程智能体运行时（TUI），针对DeepSeek V4 做了前缀缓存工程优化（长会话实测稳态命中率 95–99%）和深度适配。它跳出了传统 AI 编程助手把大模型仅当成“工具”的局限，基于认知虚拟机 (CVM)、自感知层
coding-agentdeepseekprefix-cachetoken-optimization
Zep
Memory
getzep
Examples, framework integrations, and ingestion tooling for the Zep Cloud agent memory platform
knowledge-graphtoken-optimizationtemporal-graphfact-extraction
ToolAgentic Security
Security
msoedov
Open-source vulnerability scanner that red-teams LLMs and agent workflows with jailbreak, fuzzing, and multimodal probes
red-teamfuzzingvulnerability-scanner
ToolAntigravity SDK Python
Coding
google-antigravity
A Python library for building AI agents that leverage the full power of Google Antigravity.
sdktool-callinggeminitoken-optimization
ToolContext Gateway
CodingInference
Compresr-ai
Interesting idea: context management as infrastructure, not application logic. Context Gateway runs as a transparent pro
token-optimizationproxyprompt-compression
ToolNeocarta
MemoryData Wrangling
neo4j-labs
Neocarta reads BigQuery or Snowflake schema into a semantic layer graph in Neo4j, serving...
neo4jsemantic-layerknowledge-graphtext-to-sql
ToolPandaProbe
CodingMonitoring
chirpz-ai
Open-source platform for tracing, evaluating, and monitoring AI agents, with integrations for LangGraph, CrewAI, and agent SDKs
observabilityevaluationlangchaincrewai
ToolRagent
Memory
nageoffer
Enterprise-oriented Agentic RAG platform on Spring AI covering document ingestion through question answering with multi-channel retrieval
ragspring-aidocument-ingestionhybrid-retrieval
ToolZep Python
Memory
getzep
Build Agents That Recall What Matters. Systematically engineer relevant context from chat history & business data. (Python Client)
knowledge-graphlong-term-memorychat-historyfact-extraction
ToolAgent Memory
Memory
neo4j-labs
neo4j-labs/agent-memory gives agents three memory layers in one graph: conversation histo...
knowledge-graphneo4jvector-db
ToolAutocontext
CodingQA
greyhaven-ai
Agents that start cold every run can't compound what worked. autocontext splits improvement into five roles per cycle …
token-optimizationself-improvementplaybooksevaluation-loop
ToolBeever Atlas
MemoryConnectors
Beever-AI
What if your AI agent could carry its entire knowledge base as a single versioned artifact … built with a powerful model
ragknowledge-graphslackdiscord
ToolGoogle skills
Deployment
Repository of installable agent skills for Google Cloud products, covering setup, AI/ML, GKE infrastructure, and databases
skillcloudbigquery
ToolMiles
Training
radixark
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
reinforcement-learningfine-tunevision-language-modeldistributed-training
ToolTerminal-Bench
QACoding
harbor-framework
Benchmark and harness for evaluating AI agents on end-to-end tasks in real terminal environments.
evaluationcliterminal-tasks
MCP-UI
Interface
MCP-UI-Org
Server/client SDK for embedding interactive UI resources in MCP tool responses; basis of the official MCP Apps extension.
sdkembeddable-ui