Autonomous AI agents that perform tasks independently
Saptarshi Bhattacharjee
Shared fingerprinting and storage primitives for the agentbelt suite.
tainan
The Itera Learning local agent: capture hooks, the spool, the installer and the shipper. Captures your coding-agent work and ships it to the Itera Learning engine.
...morejohn-mg
Conversational Intent Firewall for AI agents. Screen WhatsApp, Telegram, and chat messages for prompt injection, social engineering, and fraud in <10ms.
...moreAdam Campbell
Themis policy kernel for bounded-autonomy LLM agents — locks, drafts, scopes, audit. Python reference implementation of Themis RFC v0.
...morefavcrm-dev
Dependency-free transport contract and explicit fixture transport foundation. This package does not connect to a live API, handle credentials, or grant authority. Hosts supply handlers and remain responsible for authentication and policy.
...morefavcrm-dev
`GadgetSplitView.svelte` preserves Studio's bounded app/chat grid, responsive breakpoint, scroll ownership and permanently mounted app slot. Chat content is unmounted when collapsed; persistent chat state must remain host-owned. Pass localized `chatLabel`
...morefavcrm-dev
Unpublished foundation. These commands operate on **trusted local source**; they do not sandbox scripts, authorize publishing, install an agent into a workspace, or prove Cloudflare runtime compatibility. The public SDK uses owner-approved Apache-2.0; can
...moreThin OTEL wrapper for agent/LLM observability — OpenInference + GenAI semantic conventions
mycelhq
Open kernel for AI-native service businesses. OpenCode in a sandbox. The agent never holds a credential — a human sits on every send.
...moretommerty
A community driven directory of paseo.sh plugins
bloodf
OMP plugin for autonomous long-lived multi-agent collaboration
rrrrrredy
DeepSeek Harness community Bundle for local, evidence-backed Agent Memory
xiongxiongop
Official GoAnyAPI CLI for humans and AI agents
paybondai
Generic HTTP client for Haven. Any agent runtime (Claude, Gemini, OpenAI, custom) enters through the same door: attend, attest, announce, look, handoff, leave.
...moreagent-augury contributors
Model-agnostic passive awareness multi-agent runtime — concept inherited from AgentRadio (Coral-Protocol), re-implemented standalone.
...moresocial4hyq
OpenHarmony arm64 prebuilt binary for agentic-jujutsu (NAPI-RS)
A local web UI for browsing and analyzing AI coding assistant chat history
Deterministic execution control layer for governed AI-agent and software actions
lkimuk
An intelligent reverse engineering analysis tool designed for multiple target platforms, currently supporting HarmonyOS (HAP/APP/ABC) and Android (APK/AAB).
...morecofy-x
DSH-native terminal workbench (TUI) for DeepSeek Harness with durable sessions, structured tools, plans, subagents, and rotating Pokémon startup art.
...morefebruality
Free WordPress MCP server with undo — 168 tools for Claude, ChatGPT, Cursor & Claude Code. Self-hosted Model Context Protocol endpoint, no relay, no Pro tier. Install from WordPress.org.
...moreinvergent-ai
Open platform for running Managed Agents at scale
echo-yiyi
A persistent agent runtime and its official CLI. Three packages: @echo-agent/core (runtime/SDK, zero runtime dependencies), echo-agent (CLI and interactive TUI), and echo-coding (the coding-agent product).
...moreLLM Reliability Contributors
Evidence-based reliability analyzer and root-cause diagnosis engine for LLM, RAG, and Agent systems.