Coding-agent memory where every fact is a verbatim quote graded by TypeSafe Jev's calibrated confidence. Local-first, SQLite receipts, zero dependencies.
-
Updated
Sep 22, 2026 - Python
#
calibrated-confidence
Here are 7 public repositories matching this topic...
Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.
hooks mcp python3 claude developer-productivity coding-assistant ai-tools prompt-engineering anthropic ai-pair-programming mcp-server agent-memory claude-code agentic-coding agents-md claude-code-plugin llm-tooling session-continuity calibrated-confidence compliance-redaction
-
Updated
Sep 20, 2026 - Python
Agent skill for finding, building, evaluating, and improving decision-model systems. Compositional decision calculus, eval harnesses, and bounded prompt/program hill climbing for Software 3.0. TypeSafe Jev is the default hosted exemplar. Independent of TypeSafe.
typesafe formal-methods decision-theory ai-agents reranking structured-output zero-shot-classification agentic-ai agent-skills claude-code agent-workflows decision-systems claude-code-skills codex-skills cursor-skills calibrated-confidence jev typesafe-ai system-one system-one-models
-
Updated
Sep 23, 2026 - Python
mBFT: Metacognitive Byzantine Fault Tolerance — reference implementation for Consensus-Driven Metacognition in Multi-Agent Systems
python distributed-systems verification multi-agent-systems autonomous-agents ai-safety reasoning consensus-algorithm ai-agents metacognition peer-review consensus-protocol byzantine-fault-tolerance epistemic-uncertainty llm agent-coordination llm-agents hallucination-detection ml-research calibrated-confidence
-
Updated
Jun 6, 2026 - Python
Eight minimal working examples of TypeSafe's Jev (a System One model) applied to mechanical and electrical engineering: CAD/CAE/CAM routing, FEM result triage, DFM screening, BOM alignment, hallucination-proof extraction. Zero dependencies.
-
Updated
Sep 16, 2026 - Python
Make AI agents check what they actually verified before claiming something is done.
verification uncertainty developer-tools codex ai-safety ai-agents llm prompt-engineering coding-agents ai-coding agent-skills ai-skills claude-code codex-skill calibrated-confidence
-
Updated
May 2, 2026 - Shell
Minimal demo of calibrated LLM-as-a-judge scores from the single-call token-logprob distribution (Wang et al. 2025; G-Eval).
-
Updated
Jul 30, 2026 - Python
Add this topic to your repo
To associate your repository with the calibrated-confidence topic, visit your repo's landing page and select "manage topics."