Autonomous AI agents that perform tasks independently
PerryLink
Vendor parameter translation and deterministic JSON repair for DeepSeek Harness: /translate maps temperature/top_p/max_tokens/stop/system across 11 vendors, and the post-execute repair layer (plus fix_json) fixes broken JSON tool output without ever fabricating data
...morePerryLink
PII masking middleware for DeepSeek Harness: anonymize names, phones, emails, ID cards, bank cards, keys, and addresses to placeholders before they reach the model, restore them at the display layer, keep the restore table only in memory and a controlled storage domain, never log plaintext, and expose /mask and the mask_test tool
...morePerryLink
Unified static-image generation router for DeepSeek Harness: one image_generate tool with standard parameters, config-driven engine routing (OpenAI Images, Zhipu CogView, and any compatible endpoint) with health-aware fallback, durable workspace attachments, per-session quota accounting, and a Plugins settings panel
...morePerryLink
Read-only performance diagnostics for DeepSeek Harness: session load/restore timing, spill-hit counts, compaction count and trigger, context-injection volume (AGENTS.md/skills/tool-schema token share), and LLM cache hit rate — surfaced via /fast, persisted as reconstructable session events with async sampling off the model path.
...morePerryLink
Laya decision engine as a first-class Cordis service and model-visible tools for DeepSeek Harness.
Client for kept.vision keepers — versioned, signed, append-only storage for agents. Early release: the client is not published yet.
...moreThe integrity layer for your evals: fail-closed release gates with signed, tamper-evident, pre-registered receipts — for pytest, promptfoo, claude plugin eval, or any scores. Runs in any CI, no AI agent required.
...morehydra1902
Agent-plane presentation selector: composes one agent's tools as Code Mode, native, or both
Mainak Sen
Validate, repair, retry, and safely consume structured LLM output.