Runtime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
Repository Index
47,133 repositories indexed
145–168 of 177 · Most stars
Official implementation of paper "Cache Engineering for Agents"
PocketStrike is a privacy-first mobile AI workstation. It combines zero-cloud native on-device GGUF inference (ARM NEON accelerated) │ with frontier cloud LLMs, multi-step ReAct agent tools, Model Context Protocol (MCP) servers, self-evolving cross-session memory, and FLUX neural image │ generation.
TranslatedLocal-first Rust TUI/CLI for auditing AI coding-agent sessions: cost, tokens, latency, failures, and health
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
- agent-framework
- agentic-workflow
- aiforscience
- llm-agents
Investor’s Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?
Set up Claude Code once. Your whole company gets it. Self-hosted Claude Code and Codex with your company files, team skills, MCP and per-person folder permissions.
- agent-skills
- ai-workspace
- claude-code
- codex
TranslatedPi.NET is a .NET 10 port of Pi. Pi is a minimal, extensible Agent harness (a TypeScript monorepo of about 171,000 lines). This project ports its core libraries one by one to net10.0, so that the .NET ecosystem can use the same set of capabilities.
- agent
- agentic-ai
- dotnet
Fault-injected tool environments with side-effect grading for evaluating and post-training LLM agents
Evolved DSH plugin harnesses for five agent benchmarks, with versioned artifacts, evolution curves and Life-Harness comparisons
- agent-benchmark
- dsh
- harness
- leaderboard
See what your AI coding agent is doing. Multi-provider assistant & session monitor for VS Code and the terminal — inline completions, code transforms, and a full TUI dashboard tracking tokens, cost, and context across Claude Code, OpenCode, and Codex. Switch between multiple Claude Code and Codex accounts.
- copilot-alternative
- inline-completion
- claude-code-cli
- code-reviews
PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.
Open standard for Provenance & Intent Contracts (PIC) in AI agents. Verify intent, provenance, and evidence before high-impact tool calls.
- action-proposals
- agentic-ai
- agents
- ai
Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
LLM and agent evaluation for Java & Kotlin. Runs in JUnit and CI. Spring AI, LangChain4j, Koog, Embabel, and any LLM client.
- agent-evaluation
- evaluation-framework
- evaluation-metrics
- java
A Go toolkit for building AI agents and applications across multiple providers. Unified LLM client, agent framework with handoffs, tool calling, streaming, structured output, MCP integration, and cost tracking.
- ai
- golang
- llm
- structured-output
One local, searchable index of your AI coding-agent history Claude Code, Codex, Cursor, Gemini & more. Keyword + semantic search, MCP server, CLI & VS Code extension.
Test harness for voice agents. Import from Retell, VAPI, Bland, LiveKit. Run autonomous simulations. Evaluate with LLM judges.
- bland
- dspy
- livekit
- llm
Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.
- golang
- observability
- opentelemetry
- policy-engine
The production agent framework for Go — type-safe agents, structured output, multi-provider streaming, guardrails, and multi-agent orchestration with zero core dependencies.
The tested, tool-agnostic AGENTS.md kit — verified templates, a CI linter, and migrators from .cursorrules/CLAUDE.md/Copilot/Windsurf/Cline/Aider.
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
- agent-orchestration
- cli
- developer-tools
- llm-agents
🧭 Let your coding agent off the leash — not off the rails. Guardrails, a hard budget cap & a self-fixing PR loop for Claude Code / Codex / Gemini. Eval-gated 100/100, you always merge.
Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2.0, 1040 tests, F1 96.0% with 0% false positives. Docker, GitHub Action, LangChain/LlamaIndex/CrewAI integrations.
- agentic-ai
- ai-safety
- fastapi
- langchain