OneCLI – Vault for AI Agents in Rust
We built OneCLI because AI agents are being given raw API keys. And it's going about as well as you'd expect. We figured the answer isn't "don't give agents access," it's "give them access without giving them secrets."OneCLI is an open-source gateway that sits between your AI agents and the services they call. You store your real credentials once in OneCLI's encrypted vault, and give your agents placeholder keys. When an agent makes an HTTP call through the proxy, OneCLI matches the request by host/path, verifies the agent should have access, swaps the placeholder for the real credential, and forwards the request. The agent never touches the actual secret. It just uses CLI or MCP tools as normal.Try it in one line: docker run --pull always -p 10254:10254 -p 10255:10255 -v onecli-data:/app/data ghcr.io/onecli/onecliThe proxy is written in Rust, the dashboard is Next.js, and secrets are AES-256-GCM encrypted at rest. Everything runs in a single Docker container with an embedded Postgres (PGlite), no external dependencies. Works with any agent framework (OpenClaw, NanoClaw, IronClaw, or anything that can set an HTTPS_PROXY).We started with what felt most urgent: agents shouldn't be holding raw credentials. The next layer is access policies and audit, defining what each agent can call, logging everything, and requiring human approval before sensitive actions go through.It's Apache-2.0 licensed. We'd love feedback on the approach, and we're especially curious how people are handling agent auth today.GitHub: https://github.com/onecli/onecli Site: https://onecli.sh
FL score
out of 100
Verdict
high confidence
Competition
12
competitors found, emerging market, funded players
Trend
No signal yet
A Rust-based open-source vault and proxy for AI agents to securely manage API keys, addressing a critical pain point in a crowded, well-funded market.
The pain
The gap
Build angle
Strengths
- Addresses a critical and urgent security problem for AI agents.
- The proxy-based solution directly tackles the vulnerability of secrets in agent memory (prompt injection).
- Already built and open-source MVP, demonstrating technical feasibility.
- High market growth potential due to increasing AI agent adoption.
- Self-contained, minimal dependencies, and built in Rust for performance/security.
Risks
- Highly crowded market with multiple well-funded competitors offering enterprise-grade solutions.
- Lack of a clear, proven monetization model for the open-source project.
- Competition from similar open-source proxy tools (e.g., Runloop Agent Gateway).
- Enterprise clients may prefer commercially backed and supported security solutions over an open-source project.
- The effort required for ongoing development, maintenance, and competitive feature parity might be too high for a solo builder.
Next steps
- **Define and validate a specific monetization strategy**: Explore enterprise features, managed service, or support contracts for OneCLI.
- **Identify a hyper-niche paying audience**: Instead of broadly targeting 'AI agents,' focus on 'AI agents for X industry' or 'AI agents for Y specific task' where the security pain is exceptionally high and existing solutions are clearly failing/overpriced.
- **Gather explicit feedback on willingness to pay**: Conduct interviews with MLOps engineers, security leads, and AI developers in target companies to understand their budget and preferred solution types (commercial vs. open-source for security infrastructure).
- **Analyze competitor pricing and features**: Deep dive into how existing funded players differentiate and price, to find a precise commercial gap OneCLI can fill.
Fly Labs Method
Is the pain real, is there a gap, is it the right time, can one person build it.
- Problem clarity
- 26
- Solution gap
- 10
- Willingness to pay
- 19
- Buildability
- 7
High problem clarity and urgency, but the market is crowded with strong, funded players and similar open-source proxies, making a significant gap for a solo builder hard to carve out without a clear monetization path.
Value Equation
Dream outcome and how likely it feels, against the time and effort it costs.
Strong market need and timing, but weak differentiation and difficult monetization in a highly competitive landscape for a solo builder.
One-Person Business
Curiosity pull, identity fit, and a path from free value to paid for a solo creator.
Strong problem and creator fit, but monetization in a competitive enterprise market for an open-source tool presents a major hurdle for a solo builder.
Viral Frameworks
Hook strength, shareability, and how cheaply it can be tested.
Clear value proposition for a specific audience, but the open-source business model is currently undefined, and validation is needed for commercial viability in a highly competitive market.
Builder Lens
Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.
Addresses a real, desperate problem with a narrow, deployable solution, and is well-positioned for future growth in AI agent security.
Why this verdict
Five lenses, one composite. How scoring works
The angle
This weekend
- **Define and validate a specific monetization strategy**: Explore enterprise features, managed service, or support contracts for OneCLI.
- **Identify a hyper-niche paying audience**: Instead of broadly targeting 'AI agents,' focus on 'AI agents for X industry' or 'AI agents for Y specific task' where the security pain is exceptionally high and existing solutions are clearly failing/overpriced.
- **Gather explicit feedback on willingness to pay**: Conduct interviews with MLOps engineers, security leads, and AI developers in target companies to understand their budget and preferred solution types (commercial vs. open-source for security infrastructure).
- **Analyze competitor pricing and features**: Deep dive into how existing funded players differentiate and price, to find a precise commercial gap OneCLI can fill.
Who is already there, emerging market
Oasis Security provides an agentic access management (AAM) platform focused on governing how AI agents and machine identities access critical systems.
Pricing: Not publicly available, likely enterprise-focused with custom pricing.
Akeyless offers an identity security platform for machines, AI agents, and humans, providing secrets management, secretless authentication, and workload identity federation.
Pricing: Not publicly available, likely enterprise-focused with custom pricing. Mentions a 'Start Free' option for a demo.
CyberArk's solution discovers AI agents, enriches them with context, enforces least privilege access, and manages their lifecycle for comprehensive identity security.
Pricing: Not publicly available, likely enterprise-focused with custom pricing.
1Password Unified Access is a new agent security platform enabling organizations to securely deploy AI agents and automated workflows with credential, secret, and machine identity control.
Pricing: Unified Access Pro is generally available. Pricing not publicly listed; likely targets enterprise.
- Runloop Agent GatewayVisit
Agent Gateway is a security layer that proxies LLM/agent traffic, preventing agents from directly seeing sensitive credentials and enforcing outbound network policies.
Pricing: Not publicly available.
- SageVisit
Sage is an open-source tool that inserts an interception layer between an AI agent and its operations (shell commands, URL fetches, file writes), checking each action.
Pricing: Free (open-source).
- Token SecurityVisit
Token Security offers intent-based AI agent security, governing autonomous agents by aligning permissions with their intended purpose.
Pricing: Not publicly available.
Manifold is an AI Detection and Response (AIDR) platform securing autonomous AI on endpoints.
Pricing: Not publicly available.
Okta for AI Agents provides an identity layer for visibility and governance, including API Access Management and Privileged Credential Management, for AI agents.
Pricing: Available in Early Access. Pricing not publicly available.
- CencurityVisit
Cencurity is a security gateway that proxies LLM/agent traffic, detecting, masking, and blocking sensitive data and risky code patterns while logging all activity.
Pricing: Not publicly available.
Cisco's A2A Scanner is an open-source security framework that validates agent identities and inspects their communications for threats like impersonation and prompt injection.
Pricing: Free (open-source).
Auth0's Token Vault is designed for securely storing and managing tokens for third-party services, allowing AI agents to call external APIs without direct exposure to raw API keys.
Pricing: Not publicly available; part of the Auth0 platform.
What they charge
Recent news
Open-source tool Sage puts a security layer between AI agents and the OS
Help Net Security, March 09 2026
Oasis Security raises $120m Series B for AI agent access
RegTech Analyst, March 20 2026
1Password Launches Unified Access for AI Agent Security
1Password, March 17 2026
Manifold Announces $8 Million Seed Funding Round to Secure Autonomous Endpoint AI Agents at Runtime
GlobeNewswire, March 18 2026
Token Security Introduces Intent-Based Security for AI Agents
GlobeNewswire, March 18 2026
Market signals
The market for securing AI agents is rapidly growing and receiving significant investment. Recent funding rounds, like Oasis Security's $120M Series B, highlight the increasing recognition of the critical need for specialized identity and access management solutions for autonomous AI. The industry is moving beyond traditional human-centric security models to address the unique challenges posed by non-deterministic AI agents and their access to sensitive systems.
What frustrates people
- Traditional secrets managers like HashiCorp Vault, AWS Secrets Manager, and Doppler retrieve credentials, but the value still ends up in the agent's memory, making it vulnerable to prompt injection and malicious extensions.
- Static API keys are easily exposed in .env files, committed to git, and lack audit trails or secure team sharing.
- AI agents can be socially engineered through prompt injection to reveal their own credentials when hardcoded API keys are present.
- Most LLM SDKs were designed assuming a single, long-lived application instance with stable credentials, which creates security gaps for autonomous agents requiring dynamic credential refresh.
- API keys grant access based solely on possession, without verifying the entity, making them context-blind and vulnerable to replay attacks.
Semble – Code search for agents that uses 98% fewer tokens than grep
Hey HN! We (Stephan and Thomas) recently open-sourced Semble. We kept running into the same problem while using Claude Code on large codebases: when the agent can't find something directly, it falls back to grep, reading full files or launching subagents. This uses a lot of tokens, and often still misses the relevant code. There are existing tools for this, but they were either too slow to index on demand, needed API keys, or had poor retrieval quality.Semble is our solution for this. It combines static Model2Vec embeddings (using our latest static model: potion-code-16M) with BM25, fused via RRF and reranked with code-aware signals. Everything runs on CPU since there's no transformers involved. On our benchmark of ~1250 query/document pairs across 63 repos and 19 languages, it uses 98% fewer tokens than grep+read and reaches 99% of the retrieval quality of a 137M-parameter code-trained transformer, while being ~200x faster.Main features:- Token-efficient: 98% fewer tokens than grep+read- Fast: ~250ms to index a typical repo on our benchmark, ~1.5ms per query on CPU (very large repos may take longer)- Accurate: 0.854 NDCG@10, 99% of the best transformer setup we tested- MCP server: drop-in for Claude Code, Cursor, Codex, OpenCode- Zero config: no API keys, no GPU, no external servicesInstall in Claude Code with: claude mcp add semble -s user -- uvx --from "semble[mcp]" sembleOr check our README for other installation instructions, benchmarks, and methodology:Semble: https://github.com/MinishLab/sembleBenchmarks: https://github.com/MinishLab/semble/tree/main/benchmarksModel: https://huggingface.co/minishlab/potion-code-16MLet us know if you have any feedback or questions!
AI
Postgres extension for BM25 relevance-ranked full-text search
Last summer we faced a conundrum at my company, Tiger Data, a Postgres cloud vendor whose main business is in timeseries data. We were trying to grow our business towards emerging AI-centric workloads and wanted to provide a state-of-the-art hybrid search stack in Postgres. We'd already built pgvectorscale in house with the goal of scaling semantic search beyond pgvector's main memory limitations. We just needed a scalable ranked keyword search solution too.The problem: core Postgres doesn't provide this; the leading Postgres BM25 extension, ParadeDB, is guarded behind AGPL; developing our own extension appeared daunting. We'd need a small team of sharp engineers and 6-12 months, I figured. And we'd probably still fall short of the performance of a mature system like Parade/Tantivy.Or would we? I'd be experimenting long enough with AI-boosted development at that point to realize that with the latest tools (Claude Code + Opus) and an experienced hand (I've been working in database systems internals for 25 years now), the old time estimates pretty much go out the window.I told our CTO I thought I could solo the project in one quarter. This raised some eyebrows.It did take a little more time than that (two quarters), and we got some real help from the community (amazing!) after open-sourcing the pre-release. But I'm thrilled/exhausted today to share that pg_textsearch v1.0 is freely available via open source (Postgres license), on Tiger Data cloud, and hopefully soon, a hyperscalar near you:https://github.com/timescale/pg_textsearchIn the blog post accompanying the release, I overview the architecture and present benchmark results using MS-MARCO. To my surprise, we were not only able to meet Parade/Tantivy's query performance, but exceed it substantially, measuring a 4.7x advantage on query throughput at scale:https://www.tigerdata.com/blog/pg-textsearch-bm25-fu
AI
Consus (YC F24) – LLM gateway for companies handling sensitive data
Hey Hacker News! I'm Eric, the founder of Consus. We route all AI requests to ITAR restricted and controlled unclassified information (CUI) compliant infrastructure. Consus itself satisfies ITAR restrictions, and we recently completed our FedRAMP equivalency audit against the 410 FedRAMP High controls. FedRAMP High is the U.S. government’s strictest security baseline for cloud services handling sensitive unclassified data. A breach of this data could cause severe or catastrophic harm. Achieving FedRAMP equivalency, or authorization, is required before processing CUI information.Demo: https://youtu.be/6MYxJe6P4oYAerospace and defense is experiencing rapid growth. Unfortunately, most companies are struggling to use AI because of necessary data protections & compliance risk. These companies can move even faster if they could use the AI tools that most other industries take for granted.I spent most of my career prior to Consus in aerospace & defense. I launched national security payloads at SpaceX, and was an early employee at Castelion. I’ve watched first hand how compliance red-tape makes it difficult for companies to adopt new technologies and trust vendors that touch their sensitive data. For example, I worked with a satellite manufacturer that doesn’t allow any AI tools, even for non-sensitive work.Even as AI has become extremely useful over the past 9-12 months, I was surprised by how many aerospace & defense companies refused to touch it. They could see how it could be helpful, but they were scared about model providers training on their data, violating an ITAR rule, or risk losing new business because of a failed cyber assessment. These are all rational fears.There were a lot of ways to solve some/all of these problems, but we focused on building a compliant AI inference layer that can "plug" into any AI tool or workflow. Just as OpenRouter integrates with most tools, Consus can connect to tools like ChatGPT or Clau
AI
Questions about this idea?
FlyBot reads the scoring and gives you a second opinion on “OneCLI – Vault for AI Agents in Rust”.