
Masterplanner25/NodusAn orchestration DSL and embedded runtime for hosting agentic systems. Durable, inspectable workflows with deterministic step ordering, running in-process under a capability jail — the model lives in your host, not in the runtime. 30+ companion packages for memory, transport and governance.
Python★ 2↓ 3,404/moAug 17, 2026
actioncard/a2a-elixirElixir implementation of the Agent-to-Agent (A2A) protocol (https://a2a-protocol.org).
Elixir★ 19↓ 6,282/moJul 17, 2026
lofcz/LLMTornadoThe .NET library to build AI agents with 30+ built-in connectors.
C#★ 627Jul 21, 2026
msaleme/red-team-blue-team-agent-fabric540 security tests for AI agent systems — MCP, A2A, x402/L402, decision governance, benchmark integrity, skill supply chain. AIUC-1 pre-cert, NIST AI 800-2 aligned, MCP tool-poisoning reproduction. v4.9.1
Python★ 20↓ 667/moJul 20, 2026
RubyGems75Goodhealth index
Ruby★ 136Jul 16, 2026
TypeScript★ 257↓ 12.4K/moJul 27, 2026
agenticenv/agent-sdk-goAI agents in Go — Temporal for durable, crash-resilient execution or run in-process with zero setup. OpenAI, Anthropic, Gemini, Deepseek, Ollama, tools, MCP, A2A, RAG, memory, conversations, AG-UI, streaming, sub-agents & human-in-the-loop.
Go★ 38Jul 22, 2026
inference-gateway/a2aAn Agent Development Kit (ADK) allowing for seamless creation of A2A-compatible agents written in Go.
Go★ 23Jul 18, 2026
Go★ 1Jul 27, 2026
crates.io73Goodhealth index
tomtom215/a2a-rustType-safe, async Rust SDK for the Agent2Agent (A2A) protocol, built to the final v1.0.0 spec — JSON-RPC, REST, WebSocket & gRPC for building interoperable AI agents
Rust★ 19↓ 3,697/moJul 25, 2026
Python★ 0↓ 2,420/moJul 18, 2026
Go★ 2Jul 27, 2026

iowarp/clio-agentA science agent supporting any general AI agent in performing data management operations at scale. Builds upon the heritage of the IOWarp platform and proudly represents work done at Gnosis Research Center at Illinois Tech. Supported by NSF.
Python★ 9↓ 718/moSep 5, 2026

sensigo-hq/realmMake AI agents follow instructions reliably and prove what they did. State machine engine with evidence chains, multi-agent delegation, human gates, and auditable execution — via MCP or CLI.
TypeScript★ 0↓ 6,569/moSep 5, 2026
npm · PyPI · Hex +265Goodhealth index

muthuishere/toolnexusOne agent SDK, hand-ported to 7 languages — JavaScript, Python, Go, Java, C#, Elixir, Clojure — every port held to the same spec by a CI-enforced cross-port conformance suite, all seven at full tier. MCP · skills · native · HTTP · built-in · A2A tools behind one interface. Docs: https://muthuishere.github.io/toolnexus/
MDX · Clojure★ 5↓ 1,355/moSep 5, 2026
sharpTrick/parleyParley — a transport-agnostic MCP seam for messages, context sharing, and task hand-off between humans, chat bots, and coding agents. Runs on local SQLite, Redis, Matrix, XMPP, or NATS.
TypeScript★ 1↓ 14.4K/moJul 27, 2026
PyPI62Moderatehealth index
AgentX-ai/AgentX-PythonAgentX python SDK. Build multi-agent AI workforce. Run evaluation. Trace your agent. Full Observability.
Python★ 68Aug 3, 2026
YasserCR/galdorA Go-native framework for LLM agents, with OpenTelemetry observability built in.
Go★ 9Jul 16, 2026
Go · PyPI62Moderatehealth index
a2al/a2alDecentralized networking protocol for AI agents — sovereign identity, peer-to-peer capability discovery, and direct encrypted connections. Works as an MCP server.
Go · JavaScript★ 1Jul 17, 2026
crates.io · npm62Moderatehealth index

codewandler/fluxA Rust agent SDK, harness, and coding agent — safe by construction (non-bypassable authorization → approval → guarded IO).
Rust★ 2↓ 4,674/moAug 13, 2026
PyPI60Moderatehealth index
YugantM/hvtrackerAI Agent Trust Registry — independent, evidence-based trust scores for 300+ open-source AI agents. Runtime-trust calibrated (MCP, dependencies, provenance drift), with side-by-side comparison and embeddable live badges. Ranked by verifiable signals, not hype.
HTML★ 5Jul 26, 2026
npm60Moderatehealth index
TypeScript★ 0↓ 29.9K/moAug 25, 2026
npm57Moderatehealth index
TypeScript★ 9↓ 7,997/moAug 29, 2026
npm · Go57Moderatehealth index
daily-nerd/vitniThe verifiable trail of agent actions — signed, tamper-evident execution receipts for AI agents (MCP & A2A).
Go · TypeScript · JavaScript★ 1↓ 372/moJul 17, 2026
Go★ 0↓ 0/moJul 14, 2026
npm56Moderatehealth index
agledger-ai/sdkAGLedger™ SDK — Accountability and audit infrastructure for agentic systems. Patent Pending.
TypeScript★ 0↓ 2,001/moJul 15, 2026
PyPI54Moderatehealth index
lpalbou/AgoraHubAgoria: an agent-to-agent coordination hub. Named channels, per-channel shared state, an attention/obligation model, a verifiable transcript, message-driven triggering, and a git-friendly markdown mirror. Framework-agnostic (MCP + CLI + Python).
Python★ 1Jul 18, 2026
Python · Go★ 13Jul 27, 2026
npm53Moderatehealth index
TypeScript · JavaScript★ 1↓ 2,516/moJul 26, 2026
Go★ 0Jul 23, 2026