Autonomous AI agents that perform tasks independently
Rajveer Singh Saggu
Production-grade semantic caching for LLM agents — a learned equivalence classifier replaces the naive cosine threshold that causes false-positive failures.
...moreE2B sandbox integration for Deep Agents
Aravind Chakravarthy
A lightweight framework for safely enabling LLMs to analyze pandas/Polars data without exposing raw data or blindly executing generated code.
...moreTelenow
Telenow voice AI SDK for Python — place AI agent phone calls, mint browser/app call sessions, transfer & end live calls, verify webhooks, and stream your own LLM into calls (FastAPI/Django SSE helpers). Stdlib only.
...moreNative CrewAI tools for the Rine network — send, receive, discover, and run E2E-encrypted agent-to-agent conversations and groups from a CrewAI crew
...moretempguru-co
LlamaIndex tools for TempGuru event staffing: city coverage, W-2 rate ranges, booking lead times, and state labor compliance for 345+ US/CA cities, plus opt-in quote submission. No API key required.
...moreAI Total Cost of Ownership — instrumented agent metering and first-party Claude usage
Distill any code repo into a compact, secret-redacted LLM context pack — and fit it to a token budget.
mirror29
🦊 Open-source professional quant agent framework. Agents pick the factors working now to time entries, write full strategies, and evolve them in a sandbox — every order through machine approval, the LLM never on the order path. Multi-market, audit-grade.
...morethu-nmrc
Reliability harness for long-running OpenClaw agents: persistent state, strict task contracts, scheduled execution, and external validation.
...morebzcsk2
Free-first, model-adaptive coding agent runtime that makes local small LLMs work reliably with harness, checkpointing, verification, cache-aware context, and free-model fallback.
...moreH1shamM
Telegram-driven Gmail assistant — a Claude agent triages mail, drafts tone-matched replies, and books calendar events, with approve-before-act on every external action. FastAPI · AWS · ~94% test coverage.
...morejovfranco-tech
AI-native 3D satellite intelligence command center using public TLE/SGP4 data, validated LLM agent actions, mission briefs, scenario simulation and executive orbital insights.
...moreAgent Development Kit (ADK) overlay for the Agentex API — FastACP server, Temporal workflows, LLM provider integrations, observability
...moreRAG provenance, write gating, and drift detection for AI agents — EU AI Act compliance infrastructure
AIR Trust Layer for CrewAI — audit trails, data tokenization, consent gates, and injection detection
Spool contributors
Spool SDK for Python — trace LLM agent runs into the local Spool store
skill-eval contributors
Framework for evaluating agent skills across OpenCode, Claude Code, and Codex
ByteXByte
Platform-agnostic nxtlinq AI Agent core — API client, types, and orchestration ports
ByteXByte
React Native SDK for nxtlinq AI Agent — custom UI hooks and platform ports
Eloi Barti
One typed runtime API for Claude, Codex, and Antigravity agent SDKs.
LangChain
LangGraph Multi-Agent Supervisor
Dragon Lady
Read-only scanner for prompt-injection and LLM anti-analysis text in files before agent review
Credentials Manager for Claude Code — multi-token OAuth rotation and autonomous runner