
Curated reading list on making AI agents reliable in long-running work
- Free
- Open-source agent
- 4.7K GitHub stars
- AI models and LLM tooling

Curated reading list on making AI agents reliable in long-running work

Calibration test showing whether an agent says it doesn't know at the right time
Sourced AI and cloud pricing for FinOps: compare LLM costs, hosts and GPU break-even
Cheapest LLM that passes each task, with cost per successful task and pass rate
Compare LLM list prices by provider venue and tier, plus live time-to-first-token probes
Free MCP server for AI model retirement dates, repo model scans and usage-cost checks
Runs locallySearch agent skills ranked by measured lift over a no-skill baseline
Runs locallyRead-only access to NL;NL Labs' daily AI model test results for business jobs
Not checked yetMeasures where an agent session's tokens and cost go, and trims context safely
Runs locallySigned, preregistered experiments on which prompts and tools help AI agents
Not checked yetQuery one author's essays, labs, robotics data and AI benchmarks over MCP
Not checked yet
Search measured local-LLM speeds on home GPU rigs and check what will run
Not checked yetRun your own agent through six refereed jobs with hidden traps and get a report card
Not checked yetDaily prices, stock and measured speeds for computers that run local AI models
Not checked yetPractice exam and public score for AI shopping, booking and reservation agents
Not checked yetRead-only MCP catalog of agent packs graded against human expert agreement
Not checked yetCompare published prices of AI agents, MCP servers and APIs, with a daily price index
Not checked yetFree read-only MCP server for the daily LLM leaderboard, benchmarks and model comparisons
Not checked yetFind a verified web workflow and replay it with zero model calls, with failures shown
Not checked yetQuery AI inference price indexes, model prices, speed and cost per task
Not checked yetFree, key-less MCP server for sourced AI model facts and tool release briefs
Not checked yet
Directional answers on whether quantizing an LLM saves GPU energy, with stated basis
Not checked yetLook up AI agent use cases that were re-run, scored out of 10 and graded by access level
Not checked yetLook up AI model prices, context windows, licences and LMArena ranks with source links
Not checked yetSourced register of open-weight AI model releases and AI news, open to agents
Not checked yetIndependent open-weight LLM test scores: which local model fits your GPU or Mac
Not checked yetBenchmark contest where agents classify a product blurb by category and sentiment
Not checked yetDated, sourced French data on AI model prices, subscriptions, benchmarks and settings
Not checked yetFree challenge that checks agents' claims against signed receipts of their calls
Runs locallyRead-only MCP server for AI model prices, benchmark scores and independent model tests
Not checked yet