| npcsh cargo | 2.1.22 | 3 vulnerabilities 3 | The composable multi-agent shell | 987 | 2d ago |
| inferlab-proxy cargo | 0.21.0 | clean | The built-in serving proxy for Inferlab experiment topologies. | 885 | 1d ago |
| inferlab-runtime cargo | 0.21.0 | clean | Framework-neutral runtime lifecycle mechanics for the InferLab product. | 885 | 1d ago |
| everruns-contracts cargo | 0.44.0 | clean | Shared runtime, provider, capability, and model profile contracts for Everruns | 832 | 1h ago |
| bedrock-gateway-rust cargo | 0.18.1 | 4 vulnerabilities 4 | OpenAI-compatible HTTP gateway for Amazon Bedrock: Chat Completions, Responses, Completions and Embeddings from one Rust binary. | 814 | 2d ago |
| dynamo-mocker cargo | 1.5.1 | clean | Mock LLM scheduler and KV manager for testing | 812 | 22h ago |
| dekopon-agent cargo | 0.35.0 | clean | Bounded model prompt loop and session capability dispatch for Dekopon agents | 771 | 1d ago |
| inferlab-profiler cargo | 0.21.0 | clean | Nsight Systems capture planning and lifecycle for the InferLab product. | 766 | 1d ago |
| introspection-sdk cargo | 0.24.0 | clean | Rust SDK for Introspection — continuously improve your AI systems with production feedback and frontier practices | 745 | 22h ago |
| wicked-estate-mcp cargo | 0.21.0 | 4 vulnerabilities 4 | MCP server exposing the wicked-estate retrieval tools. | 698 | 1d ago |
| inferlab cargo | 0.21.0 | clean | Reproducible LLM inference experiment harness: versioned workspaces, closed-loop serve/eval/bench recipes, runtime images, and file-first evidence. | 687 | 21h ago |
| everruns-macros cargo | 0.43.0 | clean | Procedural macros for the Everruns agentic framework (re-exported by `everruns`) | 679 | 23h ago |
| phi-agent cargo | 0.18.0 | clean | phi-agent — Rust AI Agent runtime framework: orchestration, sessions, streaming built-in. You define tools, prompts, domain knowledge. | 673 | 20h ago |
| scv-cli cargo | 0.3.13 | 3 vulnerabilities 3 | A small, extensible terminal agent runtime with a TUI and headless server | 659 | 1d ago |
| inferlab-serve-domain cargo | 0.21.0 | clean | Validated serve-planning stages and frozen process execution facts for InferLab. | 626 | 1d ago |
| sigit cargo | | not built 1.6.3 did not build | siGit Code — ACP-compatible AI coding agent. Sí, git. | 553 | 1d ago |
| ikigai-passkey cargo | 0.1.39 | clean | A minimal single-user WebAuthn (ES256) assertion verifier: check a passkey assertion against one registered credential — origin, RP-ID, challenge,… | 542 | 1d ago |
| phi-kernel-tools cargo | 0.9.1 | clean | Kernel tools for phi-agent — file system, multi-agent, and shell tools | 542 | 21h ago |
| aegis-dto cargo | 0.4.5 | clean | Enrollment and runtime primitives for Aegis managed hosts. | 541 | 12h ago |
| esf-format cargo | 13.6.0 | clean | Imports EVE Online ship fits, like EFT, ESI fittings and killmails, into the dogma engine | 539 | 1d ago |
| disclude cargo | 3.0.0 | 3 vulnerabilities 3 | Static analyzer to discover obfuscation of malicious code, with LLM review and enrichment | 527 | 1d ago |
| unrager cargo | 0.31.0 | 12 vulnerabilities 12 | Takes the rage out of your x.com timeline with a local LLM: browser extension, terminal client and API server | 523 | 2d ago |
| hyperdb-mcp cargo | | not built 1.0.0-rc.5 did not build | MCP server for Hyper database — instant SQL analytics for LLM workflows | 509 | 2d ago |
| nachalnik cargo | 0.9.0 | clean | A minimal, transparent agent runtime: context, tools, permissions and execution as explicit, user-controllable state. | 478 | 20h ago |
| everruns-test-support cargo | 0.43.0 | clean | In-memory loops, test doubles, writable fixtures, and demo capabilities for testing Everruns agents | 469 | 23h ago |
| warble cargo | 0.17.0 | clean | Warble front-end compiler: parse/resolve/validate a behavior profile into language-neutral IR (sans-IO). | 466 | 16h ago |
| warble-claude-code cargo | 0.17.0 | clean | Warble back-end for the Claude Code CLI target: IR → static agent files + reference renderer + capability manifest. | 445 | 16h ago |
| warble-eval-compare cargo | 0.17.0 | clean | Warble eval comparator: compare a result-set table against a golden expectation (scalar/set/ordered match, with tolerance). | 445 | 16h ago |
| warble-eval-runner cargo | 0.17.0 | clean | Warble eval runner: replay golden questions through a dispatched agent under tier→model bindings, score, and produce a Pareto report. | 377 | 5h ago |
| rig-candle cargo | 0.44.0 | clean | Local Candle Llama, SmolLM2, and Qwen3 completion models and YOLOv8 pose estimation for Rig | 374 | 5h ago |
